© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 975
    Prev
    Next
    INDEX
    Explanations

    First Corps

    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
    llabus
    0.41
    ϩ
    0.38
    汋
    0.37
    靠近
    0.37
    রন
    0.36
    Ꮏ
    0.36
     ],"
    0.35
    ফে
    0.35
    蕲
    0.35
     Shallow
    0.35
    POSITIVE LOGITS
     thing
    0.49
     ante
    0.41
     cigar
    0.40
     imbalance
    0.38
    thing
    0.37
     Ante
    0.37
     man
    0.36
     sight
    0.35
     minute
    0.35
     week
    0.35
    Activations Density 0.000%

    No Known Activations