© 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. 196861
    Prev
    Next
    INDEX
    Explanations

    contact data and status

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

    harmful tropes, exploitation

    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
    instellung
    0.52
    钻
    0.51
    ഗീയ
    0.49
    Molecular
    0.49
    Roasted
    0.48
    〖
    0.47
    饒
    0.47
    statistic
    0.46
    Interview
    0.46
    嗓
    0.46
    POSITIVE LOGITS
     avion
    0.49
     kapal
    0.48
     ITIS
    0.48
     crocodiles
    0.48
    ль
    0.48
     auster
    0.47
     middlemen
    0.47
     Australie
    0.46
    ලය
    0.46
    ूला
    0.46
    Activations Density 0.000%

    No Known Activations