© 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. 237970
    Prev
    Next
    INDEX
    Explanations

    interventional procedure, assessing, swapping

    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
    ﺯ
    0.53
    ricorn
    0.49
    fromi
    0.49
    forme
    0.47
    ഭവ
    0.46
    केज
    0.46
    عمل
    0.46
     devrait
    0.45
    posure
    0.45
     दुरुपयोग
    0.45
    POSITIVE LOGITS
     составе
    0.56
     größten
    0.52
    стые
    0.50
    绦
    0.48
    𝙤
    0.47
     grootste
    0.47
     zahlreichen
    0.46
    ye
    0.45
     típ
    0.45
     hábitos
    0.45
    Activations Density 0.001%

    No Known Activations