© 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. 7097
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    years and months

    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
     ఆధ్యా
    0.38
    及び
    0.38
     aerobic
    0.38
    Ｕ
    0.38
    HAV
    0.37
     CFM
    0.36
     ಪೊ
    0.35
     assumptions
    0.35
    bosch
    0.35
     Lij
    0.35
    POSITIVE LOGITS
     geliyor
    0.44
     saloon
    0.38
    وعه
    0.38
    账
    0.37
    짊
    0.37
    िटल
    0.36
     editar
    0.36
    接下来
    0.35
    ранд
    0.35
     लागणार
    0.35
    Activations Density 0.006%

    No Known Activations