© 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. 88952
    Prev
    Next
    INDEX
    Explanations

    section dividers

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

    acknowledgement, hypothesis, decoding

    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
    v
    0.53
    Пор
    0.52
    amak
    0.50
    ம
    0.50
    on
    0.49
    w
    0.48
    जा
    0.48
    osal
    0.48
    Might
    0.47
    m
    0.47
    POSITIVE LOGITS
     stripes
    0.60
     tassels
    0.60
     striped
    0.58
     stripe
    0.57
     acknowledgement
    0.54
     SSO
    0.54
     tassel
    0.54
     acknowledgment
    0.52
     pajamas
    0.51
     themes
    0.50
    Activations Density 0.001%

    No Known Activations