© 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. 84214
    Prev
    Next
    INDEX
    Explanations

    date and month information

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

    key equals in code

    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
    innen
    0.62
    ō
    0.62
    ich
    0.58
    versive
    0.57
    olo
    0.55
    os
    0.55
    ov
    0.54
    oinette
    0.54
    ul
    0.53
    el
    0.52
    POSITIVE LOGITS
     getActivity
    0.56
    暠
    0.52
     setSnackbar
    0.49
    就
    0.48
    帮
    0.48
    閎
    0.46
    בת
    0.46
    দেব
    0.46
    परिवार
    0.46
    作为
    0.46
    Activations Density 0.000%

    No Known Activations