© 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. 238524
    Prev
    Next
    INDEX
    Explanations

    professional brand

    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
    陨
    0.52
    Shah
    0.51
    াউন
    0.50
    Halloween
    0.46
    Johann
    0.45
    懑
    0.44
     एनिमल्स
    0.44
    Scopes
    0.44
    ፨
    0.44
    缥
    0.44
    POSITIVE LOGITS
     hopes
    0.50
     hands
    0.49
     NGS
    0.47
     doit
    0.47
     biomark
    0.47
     păr
    0.47
    '
    0.46
    乗
    0.46
     σημα
    0.46
     drawers
    0.46
    Activations Density 0.000%

    No Known Activations