© 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. 6586
    Prev
    Next
    INDEX
    Explanations

    few, compared, small

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

    limited comparison

    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
    🅔
    0.50
    暏
    0.46
     অনন্য
    0.44
    馗
    0.43
     Calyce
    0.43
    璀
    0.43
    리를
    0.42
    볍
    0.42
     surpass
    0.42
    Timestamp
    0.42
    POSITIVE LOGITS
    compared
    0.97
     compared
    0.97
    少ない
    0.88
     Compared
    0.80
    Compared
    0.76
     paltry
    0.74
     meagre
    0.73
     meager
    0.72
     குறைவாக
    0.71
     น้อย
    0.71
    Activations Density 0.201%

    No Known Activations