© 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. 255395
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     tái
    0.52
     এটির
    0.46
     அவருக்கு
    0.45
     இருக்கிறார்
    0.45
     নিজেই
    0.44
     baggy
    0.44
    恕
    0.44
     आला
    0.43
     動物
    0.43
     hemoglobin
    0.42
    POSITIVE LOGITS
    테
    0.52
    н
    0.49
    зон
    0.48
    ן
    0.48
    ته
    0.46
     도로
    0.46
    .{
    0.44
     STORE
    0.44
    ፁ
    0.44
    ing
    0.44
    Activations Density 0.000%

    No Known Activations