© 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. 104155
    Prev
    Next
    INDEX
    Explanations

    family members

    np_acts-logits-general · gemini-2.5-flash-lite

    might be, wants to, linked list

    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
    s
    0.49
    -
    0.48
    journal
    0.46
    thers
    0.46
     journal
    0.46
    taught
    0.46
    la
    0.45
     proving
    0.45
     pect
    0.45
     therm
    0.44
    POSITIVE LOGITS
    醯
    0.53
     மனதில்
    0.50
    ²',
    0.47
     Huyền
    0.45
    কোনও
    0.45
     ناقابل
    0.45
    海の
    0.45
     офі
    0.44
     категорії
    0.44
     DON
    0.44
    Activations Density 0.001%

    No Known Activations