© 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. 5865
    Prev
    Next
    INDEX
    Explanations

    don't or don name

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

    don't

    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
    ebilir
    0.41
    冚
    0.41
    รียน
    0.40
    学的
    0.40
    літи
    0.38
    বাংলাদেশের
    0.38
    ().
    0.37
    ラク
    0.37
    esinin
    0.37
     newApproved
    0.37
    POSITIVE LOGITS
    derdag
    0.70
    ’
    0.65
    keys
    0.63
    ahue
    0.63
    ald
    0.61
    ating
    0.58
    ovan
    0.58
    nelly
    0.58
    atello
    0.56
    key
    0.55
    Activations Density 0.036%

    No Known Activations