© 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. 206262
    Prev
    Next
    INDEX
    Explanations

    cooking, pottery, meter, sharing, truffles

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

    update less might blastoma

    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
     historia
    0.47
     basicamente
    0.47
    ைப்
    0.46
     vý
    0.45
    필
    0.45
    vý
    0.44
     personnages
    0.44
     bunlar
    0.44
     tranquila
    0.44
     basiert
    0.44
    POSITIVE LOGITS
    뇰
    0.49
    houette
    0.47
    MNumber
    0.45
    ᾰ
    0.44
    夆
    0.44
     FET
    0.44
    峯
    0.43
    rolyte
    0.42
    体力
    0.42
    ériment
    0.42
    Activations Density 0.000%

    No Known Activations