© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3417
    Prev
    Next
    INDEX
    Explanations

    radical, necro, resources, lower, complex, Representatives

    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_53_width_65k_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
    !",
    0.47
     !",
    0.47
    !");
    0.45
     !,
    0.45
    ')",
    0.41
    pren
    0.40
    !...
    0.39
     superiors
    0.39
    ម្ត
    0.39
     honest
    0.39
    POSITIVE LOGITS
    Temporal
    0.44
    खा
    0.42
     Barre
    0.42
     BART
    0.41
    굽
    0.40
     동일
    0.39
    EMAN
    0.39
    ํ
    0.39
    timelist
    0.38
     バー
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.