© 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. 99555
    Prev
    Next
    INDEX
    Explanations

    family, parents, helplessness

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

    brutalization, without informed consent, prior years

    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
     Ñ
    0.50
    íd
    0.49
    arians
    0.49
     D
    0.48
    ambra
    0.48
     Gl
    0.48
    v
    0.48
     renters
    0.47
     truckers
    0.47
    Begriffsklär
    0.46
    POSITIVE LOGITS
    悩
    0.50
    交流
    0.49
    家庭
    0.47
    getParent
    0.46
    听到
    0.46
    爸爸
    0.46
     والدین
    0.44
    変
    0.44
     رسیده
    0.43
     helplessness
    0.42
    Activations Density 0.003%

    No Known Activations