© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 116348
    Prev
    Next
    INDEX
    Explanations

    fundamental issuesNovel avianEssential ECGPonte VistaQ:

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects phrases expressing a financial comeback or return to prominence (e.g. “back in reckoning,” “back in,” “on low base,” “steady sequential growth”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogh
    -0.91
    naw
    -0.88
    ፫
    -0.88
     คา
    -0.88
    ígeno
    -0.87
    ブーツ
    -0.85
     travailleurs
    -0.85
     элементы
    -0.84
    ꙑ
    -0.84
    <0xED>
    -0.83
    POSITIVE LOGITS
     ~
    0.98
     !!
    0.91
     (~
    0.91
    Ahoj
    0.90
     ((
    0.86
     gives
    0.85
     comforted
    0.84
     hypothesis
    0.82
     terrible
    0.82
     il
    0.81
    Activations Density 0.007%

    No Known Activations