© 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. 46926
    Prev
    Next
    INDEX
    Explanations

    building and managing operations

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

    spectrum shifts

    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
     Rhodesia
    0.53
    ẹ̀
    0.50
     sesuatu
    0.46
    quando
    0.45
    англ
    0.45
    悹
    0.44
     indag
    0.44
    tać
    0.44
     Rfc
    0.44
    しかった
    0.43
    POSITIVE LOGITS
    \%
    0.44
     spliced
    0.43
     handshake
    0.43
    라인
    0.42
     candle
    0.42
     traded
    0.41
     hand
    0.41
     කිරීමට
    0.41
     externally
    0.41
     drenched
    0.41
    Activations Density 0.000%

    No Known Activations