© 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. 169250
    Prev
    Next
    INDEX
    Explanations

    creating lists and descriptions

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

    argument structure: consequent, sequence, fallacy

    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
    лимп
    0.58
    
    0.57
    浈
    0.56
    嚗
    0.54
    颞
    0.53
    몄
    0.50
    쯜
    0.50
     nahilalakip
    0.50
    <unused47>
    0.50
    츰
    0.49
    POSITIVE LOGITS
    S
    0.59
     .
    0.59
    ↵
    0.55
    .
    0.53
    Y
    0.53
    ).
    0.52
     a
    0.51
     nothing
    0.51
    ek
    0.50
     data
    0.50
    Activations Density 0.000%

    No Known Activations