© 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. 104097
    Prev
    Next
    INDEX
    Explanations

    organization and training

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

    users sharecurrent investigation

    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
    ва
    0.49
    decomp
    0.46
    ка
    0.45
     pivot
    0.45
    鯢
    0.44
     tie
    0.43
    で見
    0.42
    withTrashed
    0.42
    bygg
    0.42
    ;*/
    0.41
    POSITIVE LOGITS
    нням
    0.55
    원을
    0.51
    Gosudarstvennyj
    0.49
     arrogance
    0.49
     ราช
    0.48
     dicembre
    0.47
     Ім
    0.47
     ہے۔
    0.46
     concentric
    0.46
    რავ
    0.45
    Activations Density 0.000%

    No Known Activations