© 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. 6464
    Prev
    Next
    INDEX
    Explanations

    informative

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

    explicit or graphic sexual acts

    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
     ট্যাবলেট
    0.42
     daug
    0.39
    isselle
    0.39
     كلم
    0.39
     currentRow
    0.39
    dac
    0.39
     Frag
    0.38
    ])));
    0.38
    ](
    0.38
    veni
    0.38
    POSITIVE LOGITS
    Wins
    0.45
    รรม
    0.43
     まあ
    0.38
    ogens
    0.37
    jir
    0.37
    ⅛
    0.37
     ʼ
    0.36
    informative
    0.35
     xiv
    0.35
     isteyen
    0.35
    Activations Density 0.006%

    No Known Activations