© 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. 200722
    Prev
    Next
    INDEX
    Explanations

    physical quantities and units

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

    email drafts

    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
    0.64
    the
    0.55
    0
    0.52
     three
    0.49
    1
    0.47
     nodal
    0.46
     semplicemente
    0.46
    ilat
    0.45
    are
    0.45
     intravenous
    0.44
    POSITIVE LOGITS
    时间的
    0.59
    sendPluginResult
    0.47
    债
    0.46
    餮
    0.46
    搭载
    0.46
    据悉
    0.46
    犮
    0.45
    缥
    0.45
    鼍
    0.45
    磋商
    0.45
    Activations Density 0.006%

    No Known Activations