© 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. 193814
    Prev
    Next
    INDEX
    Explanations

    customizable, a, absolute, essential, perfect

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

    consent and relationship dynamics

    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
    code
    0.62
    guid
    0.58
     be
    0.56
    nome
    0.52
    ;
    0.52
     as
    0.50
    result
    0.50
    the
    0.50
    grade
    0.49
     its
    0.49
    POSITIVE LOGITS
     প্রত্যক্ষ
    0.51
     পরিশ্রম
    0.50
    悰
    0.49
    鳝
    0.48
    欱
    0.46
     డబ్బు
    0.46
    酊
    0.45
    钠
    0.45
    恽
    0.45
    地产
    0.44
    Activations Density 0.001%

    No Known Activations