© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 6976
    Prev
    Next
    INDEX
    Explanations

    book titles and descriptions

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

    book titles and references

    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
    <unused76>
    0.61
    ಬೇವಿನ
    0.60
    <unused11>
    0.58
    <unused26>
    0.57
    <unused96>
    0.57
    sklär
    0.57
    merksamkeit
    0.56
    rbrakk
    0.56
    <start_of_turn>
    0.55
    Strafpunkte
    0.55
    POSITIVE LOGITS
     A
    0.79
     S
    0.78
    ,
    0.75
     I
    0.74
     
    0.72
     B
    0.69
     P
    0.67
     T
    0.67
     N
    0.66
     s
    0.65
    Activations Density 0.009%

    No Known Activations