© 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. 13448
    Prev
    Next
    INDEX
    Explanations

    writing essay facts

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

    usually specific descriptions

    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
     imperio
    0.51
    造型
    0.48
    то
    0.48
    が入
    0.48
    瑤
    0.47
    團隊
    0.46
    一手
    0.46
    用心
    0.45
    clientHeight
    0.45
    營
    0.45
    POSITIVE LOGITS
    nY
    0.63
    et
    0.55
    ys
    0.54
    esh
    0.53
    ary
    0.52
    ess
    0.50
    oy
    0.49
    ås
    0.49
    ou
    0.48
    ouz
    0.48
    Activations Density 0.000%

    No Known Activations