© 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. 135877
    Prev
    Next
    INDEX
    Explanations

    code, again, announced, holes

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

    foreign languages and technical terms

    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
    -
    0.46
     goalkeeper
    0.44
     benefiting
    0.43
     nurturing
    0.41
    :
    0.40
     negotiated
    0.40
    ಾರು
    0.40
     inférieure
    0.40
     customarily
    0.40
     attracted
    0.40
    POSITIVE LOGITS
    שׁ
    0.52
    腫
    0.51
    兒子
    0.48
    دو
    0.47
    镊
    0.47
    龅
    0.47
    CHILD
    0.46
    ك
    0.46
    入了
    0.46
    铰
    0.46
    Activations Density 0.000%

    No Known Activations