© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48480
    Prev
    Next
    INDEX
    Explanations

    Grasp the Sparrow’s Tail

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    Bulb
    -0.85
    itored
    -0.83
    bulb
    -0.82
    メモリ
    -0.79
    模样
    -0.79
    霁
    -0.78
    Hb
    -0.77
    Jz
    -0.76
     Soleil
    -0.76
    encias
    -0.76
    POSITIVE LOGITS
     ilç
    0.85
    stalgia
    0.82
     autumn
    0.81
     thousands
    0.79
     aquesta
    0.79
     shaded
    0.76
     adecuados
    0.75
    راحل
    0.75
    ähte
    0.74
     slant
    0.73
    Activations Density 0.009%

    No Known Activations