© 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. 5596
    Prev
    Next
    INDEX
    Explanations

    doing, solving, applying

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

    offer, introduce, begin, answer

    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
    が集
    0.19
    が含ま
    0.17
    を受け
    0.17
    が出
    0.16
    を満
    0.16
    産
    0.16
     renseign
    0.15
    にして
    0.15
    を集
    0.15
    を除
    0.15
    POSITIVE LOGITS
     পারেনি
    0.18
    নমেন্ট
    0.17
     अराउंड
    0.17
    ᵚ
    0.16
    িত্যক্ত
    0.15
    ARY
    0.15
     begyn
    0.15
    能力的
    0.15
    বায়
    0.15
    अमेर
    0.15
    Activations Density 0.004%

    No Known Activations