© 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. 98404
    Prev
    Next
    INDEX
    Explanations

    local places and structures

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

    answering queries or providing responses

    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
    nél
    0.48
    ቻ
    0.47
     manquer
    0.46
     génération
    0.46
    imidazol
    0.46
    ühm
    0.46
     člán
    0.44
    nál
    0.44
     Loving
    0.44
     Urlaub
    0.43
    POSITIVE LOGITS
    σ
    0.52
    ១
    0.51
     הס
    0.50
     agree
    0.49
     encounter
    0.47
     however
    0.46
     الس
    0.46
    year
    0.46
    LineEdit
    0.46
    ;}
    0.45
    Activations Density 0.000%

    No Known Activations