© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-65K
    4. 3799
    Prev
    Next
    INDEX
    Explanations

    directions with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    يف
    0.35
    }:
    0.33
     includ
    0.31
     includes
    0.30
     (
    0.28
     Eine
    0.28
    ূল্যে
    0.28
     Astrid
    0.28
     malfunctioning
    0.28
    }:$
    0.28
    POSITIVE LOGITS
    PORT
    0.29
    EVER
    0.28
     ئە
    0.28
     яхшы
    0.28
    wq
    0.27
    ନ୍ଦ
    0.27
    😤
    0.27
     বাজারের
    0.27
    每一个
    0.26
    centerY
    0.26
    Activations Density 2.005%

    No Known Activations