© 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. 255808
    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
     shrink
    0.42
     sid
    0.42
     drained
    0.42
    Ic
    0.41
    Descriptor
    0.41
    ocrine
    0.40
    ş
    0.40
    å
    0.40
     Sidney
    0.40
    Interfaz
    0.40
    POSITIVE LOGITS
     имущества
    0.58
     ಸಾಮಾ
    0.54
     ساق
    0.54
     เหตุ
    0.53
     społ
    0.52
     個人
    0.50
     тела
    0.50
     एलान
    0.50
    Ⅼ
    0.49
    뼈
    0.49
    Activations Density 0.000%

    No Known Activations