© 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. 100521
    Prev
    Next
    INDEX
    Explanations

    organization or listing details

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

    technical term context

    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
    portions
    0.47
    str
    0.47
    ôn
    0.46
     막
    0.46
     όχι
    0.45
    antic
    0.45
    م
    0.44
    esto
    0.44
    adians
    0.43
    보
    0.42
    POSITIVE LOGITS
    ńca
    0.52
     rencana
    0.48
     brauch
    0.48
     çalışma
    0.48
    َرْ
    0.48
    ۜ
    0.47
     typing
    0.45
     Bavaria
    0.45
     cillum
    0.45
    搭载
    0.45
    Activations Density 0.001%

    No Known Activations