© 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. 111503
    Prev
    Next
    INDEX
    Explanations

    acidic prevents

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

    compositional creation

    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
    必要な
    0.48
     Physique
    0.45
    会員
    0.44
    贵的
    0.44
    骑士
    0.44
    事情
    0.44
    StartZ
    0.44
    詆
    0.44
     stationed
    0.43
    กีฬา
    0.43
    POSITIVE LOGITS
     creates
    0.52
     content
    0.50
     creando
    0.50
     balance
    0.50
    pixels
    0.48
    resist
    0.48
    ἓ
    0.47
    content
    0.46
    balance
    0.46
    uant
    0.44
    Activations Density 0.001%

    No Known Activations