© 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. 152435
    Prev
    Next
    INDEX
    Explanations

    placing lists, sites, or stars

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

    about understanding

    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
     sessão
    0.54
     bri
    0.51
     direttore
    0.48
    <unused67>
    0.46
     miliardi
    0.46
     impar
    0.46
     rivest
    0.46
     settimana
    0.45
     dió
    0.44
     fracción
    0.44
    POSITIVE LOGITS
    ok
    0.45
    rukt
    0.45
    getTitle
    0.45
    awks
    0.44
    jär
    0.43
    }])
    0.42
    aceous
    0.42
    setTitle
    0.42
    opub
    0.42
    veer
    0.42
    Activations Density 0.001%

    No Known Activations