© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 86955
    Prev
    Next
    INDEX
    Explanations

    Rectangle flags

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

    specifying audience for recommendations

    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
     toneladas
    0.57
     assaulted
    0.52
    理由は
    0.51
    <unused46>
    0.50
     парамет
    0.50
     لیګ
    0.50
     আশ্র
    0.50
    ת
    0.49
    ꔰ
    0.49
     ओवरटाइम
    0.48
    POSITIVE LOGITS
     unifying
    0.43
    揭
    0.42
    pairing
    0.42
     vint
    0.41
    opa
    0.40
    software
    0.40
    distortion
    0.40
     vign
    0.39
    ofs
    0.39
     angg
    0.39
    Activations Density 0.000%

    No Known Activations