© 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. 164509
    Prev
    Next
    INDEX
    Explanations

    medically assisted

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

    technical writing, SQL injection, vibrators

    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
     chon
    0.49
    羔
    0.47
    اريخ
    0.46
     backgrounds
    0.44
    ｔ
    0.42
    ᾰ
    0.42
    тни
    0.41
    泮
    0.41
    ربية
    0.41
     bungalows
    0.41
    POSITIVE LOGITS
    3
    0.54
     Escobar
    0.48
    ESH
    0.48
    EN
    0.47
    total
    0.47
    Josef
    0.46
     legalized
    0.46
     sweetheart
    0.46
    September
    0.46
    uyendo
    0.46
    Activations Density 0.000%

    No Known Activations