© 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. 188214
    Prev
    Next
    INDEX
    Explanations

    destination or origin

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

    eventually removed from power

    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
    ors
    0.51
     MCSF
    0.50
    OR
    0.47
     wren
    0.47
     w
    0.46
     wf
    0.46
     bueno
    0.46
    पा
    0.45
     ESP
    0.45
    $\
    0.44
    POSITIVE LOGITS
    высо
    0.50
    ították
    0.48
    dessous
    0.46
     ప్రత్యేక
    0.46
    نجليزية
    0.45
    keszt
    0.45
    llbracket
    0.45
    噻
    0.44
    힣
    0.43
    фіка
    0.43
    Activations Density 0.000%

    No Known Activations