© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 14375
    Prev
    Next
    INDEX
    Explanations

    use

    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_16_width_262k_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
    in
    0.30
    σε
    0.25
     यंग
    0.25
     Bigg
    0.24
    น้อย
    0.23
    ʏ
    0.23
    यात
    0.23
     Norweg
    0.23
    ą
    0.22
     ByteBuffer
    0.22
    POSITIVE LOGITS
     is
    0.37
     and
    0.35
     of
    0.33
     an
    0.30
     has
    0.29
     that
    0.28
    0.28
     stato
    0.27
     t
    0.27
    O
    0.26
    Activations Density 0.060%

    No Known Activations