© 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. 145347
    Prev
    Next
    INDEX
    Explanations

    numbers and specifics

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

    . art, message, talents, story

    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
     Whelan
    0.49
    zter
    0.46
    ෝ
    0.46
    㗽
    0.45
    thyl
    0.43
    ėti
    0.42
     udziel
    0.42
    ilta
    0.42
    飨
    0.42
    坭
    0.42
    POSITIVE LOGITS
    q
    0.53
    .........
    0.52
    j
    0.51
    ைப்
    0.50
    uc
    0.50
    *{\
    0.48
    ~!
    0.48
    DOE
    0.47
    .....
    0.46
    gp
    0.45
    Activations Density 0.000%

    No Known Activations