© 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
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 8663
    Prev
    Next
    INDEX
    Explanations

    fact of the matter is

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

    fact that followed by observation

    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
    Wrist
    0.45
    禊
    0.43
    ldecode
    0.42
    わる
    0.41
     visione
    0.40
    シフト
    0.40
    媤
    0.40
    nji
    0.40
    wif
    0.39
    )}^{\
    0.39
    POSITIVE LOGITS
    ually
    0.92
    oid
    0.86
    oids
    0.83
    otum
    0.79
    itious
    0.78
    ious
    0.72
     checkers
    0.70
     sheet
    0.68
     sheets
    0.65
     Sheet
    0.63
    Activations Density 0.020%

    No Known Activations