© 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. 4173
    Prev
    Next
    INDEX
    Explanations

    for the specific purpose

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

    emergent abilities

    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
    Congrats
    0.47
     Congrats
    0.47
    <strong>
    0.46
     Emoji
    0.44
    させて頂
    0.43
     début
    0.43
     (*
    0.43
     👉
    0.43
     ज्योतिष
    0.43
     Esports
    0.42
    POSITIVE LOGITS
     kerosene
    0.47
     umana
    0.46
    每一個
    0.44
     fuelwood
    0.44
     všech
    0.43
     moradores
    0.43
     keine
    0.42
     wszystkich
    0.42
     foodstuffs
    0.42
     altijd
    0.42
    Activations Density 0.000%

    No Known Activations