© 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. 168333
    Prev
    Next
    INDEX
    Explanations

    predicting next word or phrases

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

    technical documentation and explanations

    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
     vagy
    0.47
    뭔
    0.46
    හැ
    0.46
     articol
    0.46
    Kamu
    0.44
    杯
    0.44
     тяжё
    0.44
    plicit
    0.43
     sexe
    0.43
    择
    0.43
    POSITIVE LOGITS
    lamb
    0.52
     blossomed
    0.46
    MinIntensity
    0.46
     tails
    0.44
    主席
    0.43
    amber
    0.43
     seclusion
    0.43
    blasts
    0.42
    lattice
    0.42
     دوستان
    0.42
    Activations Density 0.000%

    No Known Activations