© 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. 197015
    Prev
    Next
    INDEX
    Explanations

    numbers and specific items

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

    how good or bad

    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
    vintage
    0.51
    Vintage
    0.50
    }^{-}
    0.49
     Vintage
    0.48
    ine
    0.47
     pedibusque
    0.46
    ఠ
    0.46
    unix
    0.46
    ⵄ
    0.45
    íe
    0.45
    POSITIVE LOGITS
     mendengar
    0.51
     piano
    0.50
     accepting
    0.49
     buying
    0.48
     parap
    0.48
     this
    0.47
     emotion
    0.47
     parab
    0.46
    WIS
    0.46
     impersonal
    0.46
    Activations Density 0.003%

    No Known Activations