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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 7389
    Prev
    Next
    INDEX
    Explanations

    words ending in x

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

    sexually explicit content

    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
    tt
    0.46
    tte
    0.44
    tR
    0.42
    ર્મ
    0.41
    t
    0.41
    Pacific
    0.40
    tic
    0.40
    차
    0.40
    복
    0.40
    particular
    0.40
    POSITIVE LOGITS
    ercise
    0.87
    NUMX
    0.86
    es
    0.84
    cellent
    0.79
    ercises
    0.75
    iliary
    0.72
    treme
    0.70
    calibur
    0.69
    adecimal
    0.69
    ytocin
    0.68
    Activations Density 0.247%

    No Known Activations