© 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. 149521
    Prev
    Next
    INDEX
    Explanations

    predicting subsequent words

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

    requirements and specific contexts

    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
    ValueOf
    0.52
    epage
    0.49
    OfMonth
    0.47
    pretrained
    0.46
    frac
    0.46
    ḍ
    0.45
    𝐘
    0.45
     প্রকার
    0.45
    ok
    0.45
    ajt
    0.45
    POSITIVE LOGITS
     assailant
    0.47
     athletics
    0.47
    핫
    0.46
    рян
    0.45
     athletic
    0.45
    лян
    0.45
    邢
    0.44
     Currents
    0.44
     desarrollo
    0.43
     Pipeline
    0.42
    Activations Density 0.000%

    No Known Activations