© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4206
    Prev
    Next
    INDEX
    Explanations

    media recommendations

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

    code and markdown structuring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused96>
    0.51
    DanhMucSP
    0.50
    હાસ
    0.48
     yanlı
    0.48
    <unused9>
    0.48
    ractable
    0.47
    ণ্ঠে
    0.46
     explosives
    0.45
    hnten
    0.45
     atthakath
    0.45
    POSITIVE LOGITS
    1
    0.61
     Media
    0.58
     media
    0.55
    0.54
    C
    0.54
    E
    0.54
    Media
    0.53
    2
    0.52
     C
    0.51
    .
    0.51
    Activations Density 0.000%

    No Known Activations