© 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. 114608
    Prev
    Next
    INDEX
    Explanations

    shall not fear

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

    fetch vertices or water

    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
    श्याम
    0.45
    ૬
    0.45
    DAC
    0.45
     איי
    0.44
    SOUND
    0.44
    밴
    0.44
    OE
    0.44
    러
    0.44
    AAC
    0.43
    ราม
    0.43
    POSITIVE LOGITS
     conclusão
    0.49
     mudança
    0.48
     simplesmente
    0.46
     Hawke
    0.44
     meia
    0.43
     transmissão
    0.43
     Schluss
    0.43
     Hats
    0.43
     schimb
    0.42
    mittag
    0.42
    Activations Density 0.001%

    No Known Activations