© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 87506
    Prev
    Next
    INDEX
    Explanations

    phrases starting with capitalized words

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

    sexually explicit story

    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_31_width_262k_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
    hteet
    0.49
    knings
    0.47
    க்கர
    0.46
    วี
    0.46
    高さ
    0.45
    戦
    0.45
    าล
    0.44
    estamp
    0.43
    Obs
    0.43
    ager
    0.42
    POSITIVE LOGITS
     leto
    0.47
     offshore
    0.43
     uninsured
    0.43
     affiliates
    0.42
     wholly
    0.42
    <0x0C>
    0.42
    ର୍
    0.41
     urgente
    0.41
     серию
    0.40
    }$,
    0.39
    Activations Density 0.003%

    No Known Activations