© 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. 79318
    Prev
    Next
    INDEX
    Explanations

    regions (

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

    key how

    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
    Hem
    0.48
    ై
    0.46
    лэ
    0.44
    ֵ
    0.44
    ού
    0.44
    ح
    0.44
     hems
    0.44
    ής
    0.43
    ޕ
    0.43
    هم
    0.43
    POSITIVE LOGITS
    0.45
     विवाद
    0.45
     također
    0.45
     یخ
    0.44
     tekrar
    0.42
     فراموش
    0.42
     beschrieben
    0.41
     inaccur
    0.41
     nedeniyle
    0.41
     posthum
    0.41
    Activations Density 0.000%

    No Known Activations