© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 126399
    Prev
    Next
    INDEX
    Explanations

    class constructors and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    êtes
    0.46
    żej
    0.44
     berarti
    0.44
    زیز
    0.44
     asks
    0.43
    และการ
    0.43
    żą
    0.43
    쩝
    0.43
    𝚔
    0.42
    kę
    0.42
    POSITIVE LOGITS
     austenitic
    0.45
    Screw
    0.45
    CL
    0.44
    ATER
    0.43
     pacemaker
    0.43
    Corp
    0.42
    ITAL
    0.42
     topsail
    0.42
     trumpet
    0.41
    omile
    0.41
    Activations Density 0.006%

    No Known Activations