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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70537
    Prev
    Next
    INDEX
    Explanations

    minimum size, java phone, not working, without doors

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

    The neuron activates on terms associated with academic or research writing (e.g. thesis, dissertation, research paper, template).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    pantalon
    -1.09
    rrrrr
    -1.03
    gapi
    -1.02
    больше
    -1.01
     Миха
    -0.97
     either
    -0.97
    rrrrrr
    -0.97
    _{(
    -0.96
    茴
    -0.95
     निम्नलिखित
    -0.94
    POSITIVE LOGITS
    ポイントは
    0.98
     guerras
    0.98
    '],
    0.94
    Beskrivelse
    0.93
     llevará
    0.93
    ละเอ
    0.92
    ],
    0.91
    řen
    0.90
    UDAD
    0.88
    unked
    0.88
    Activations Density 0.030%

    No Known Activations