© 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. 73719
    Prev
    Next
    INDEX
    Explanations

    models, oppression, realities

    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
    口感
    0.47
    خدام
    0.47
    제품
    0.46
    ាហ
    0.46
    в
    0.45
    ต่างๆ
    0.44
     جهاز
    0.43
    reactor
    0.43
    𝐧
    0.42
    erà
    0.42
    POSITIVE LOGITS
     unlike
    0.46
     substantive
    0.45
     another
    0.43
    ﺵ
    0.41
     Succeed
    0.41
     antecedent
    0.40
    厲
    0.40
    alie
    0.40
     vignette
    0.40
    bring
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.