© 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. 46330
    Prev
    Next
    INDEX
    Explanations

    engineering careers and events

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

    codes and conventions in media

    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
     सांसद
    0.55
    Ⲱ
    0.52
    安裝
    0.48
    歌手
    0.46
     खासदार
    0.45
    考生
    0.45
     tussen
    0.45
    ⱪ
    0.44
     można
    0.44
     ശിഷ്യ
    0.44
    POSITIVE LOGITS
     Model
    0.46
     Jr
    0.46
    an
    0.45
     Crossed
    0.42
     Value
    0.42
     Raw
    0.41
     Clas
    0.41
    inas
    0.40
     Girl
    0.40
     Cross
    0.40
    Activations Density 0.000%

    No Known Activations