© 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. 73992
    Prev
    Next
    INDEX
    Explanations

    don't be fooled or believe

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

    don't mistake

    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
    吗
    0.55
     sicuramente
    0.52
    不少
    0.48
    其余
    0.47
    嗎
    0.46
     অসংখ্য
    0.45
    确实
    0.44
    ariski
    0.44
    至少
    0.44
    么
    0.44
    POSITIVE LOGITS
     yourself
    0.45
     Déc
    0.44
     limitations
    0.43
     grasses
    0.43
     formulations
    0.41
     Tempt
    0.40
     nays
    0.39
     discouraged
    0.39
     unconventional
    0.39
     conmigo
    0.39
    Activations Density 0.083%

    No Known Activations