© 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. 16223
    Prev
    Next
    INDEX
    Explanations

    suicide attempts

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

    following common introductory phrases

    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
    蝮
    0.51
     vuttam
    0.50
    }*/
    0.47
     başlayalım
    0.46
     Mercur
    0.46
    达
    0.46
     Lavender
    0.45
    的支持
    0.45
    '-
    0.44
     床
    0.44
    POSITIVE LOGITS
    quoi
    0.50
     enfim
    0.49
     fermeture
    0.45
    moins
    0.45
     बदला
    0.44
     संग
    0.43
    ৈর
    0.43
    ombres
    0.42
    TIMEOUT
    0.42
    ungnya
    0.42
    Activations Density 0.000%

    No Known Activations