© 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. 124725
    Prev
    Next
    INDEX
    Explanations

    change or transformation

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

    specialkeywordsorparameters

    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
    ABILITIES
    0.43
    grat
    0.43
     variegated
    0.42
    TER
    0.42
     irritation
    0.42
     irritability
    0.41
    MTAB
    0.41
     款
    0.41
     मुझ
    0.41
     πυ
    0.41
    POSITIVE LOGITS
     chiffres
    0.58
    例えば
    0.55
     있지만
    0.53
     ولكن
    0.50
    histoire
    0.48
    ارا
    0.47
     mesela
    0.46
     cria
    0.46
    ه
    0.46
    年来
    0.46
    Activations Density 0.000%

    No Known Activations