© 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. 163111
    Prev
    Next
    INDEX
    Explanations

    license termination, Paris, trains, loan eligibility

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

    conclusions and time-based information

    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
     QuantityOnHand
    0.49
    ётся
    0.47
    Assign
    0.45
    цыі
    0.45
    Bottom
    0.44
    MutableArray
    0.44
     addTo
    0.44
    𝙮
    0.44
    Posting
    0.44
     ದಾ
    0.44
    POSITIVE LOGITS
    時には
    0.53
     internation
    0.41
     sometimes
    0.40
     travellers
    0.40
    レート
    0.39
    Ｖ
    0.39
     V
    0.39
     international
    0.39
     multil
    0.38
    雑誌
    0.38
    Activations Density 0.001%

    No Known Activations