© 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. 131878
    Prev
    Next
    INDEX
    Explanations

    graphic, investigative, feature, wedding, she

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

    harm or despair

    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
    erei
    0.45
    vega
    0.44
    leon
    0.44
    fds
    0.44
     noin
    0.44
     হান
    0.43
     Horde
    0.43
     €
    0.42
     geg
    0.42
    τρο
    0.42
    POSITIVE LOGITS
    今後
    0.45
    പ്പിക്കുന്ന
    0.45
    ෞ
    0.44
     unavailable
    0.42
    व्यक्तित्व
    0.42
    靓
    0.42
    Przypisy
    0.42
     Secundaria
    0.42
     প্রথমেই
    0.41
    }}^{*}\
    0.41
    Activations Density 0.001%

    No Known Activations