© 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. 77760
    Prev
    Next
    INDEX
    Explanations

    commands and replacements

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

    likes to or cools

    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
     signatories
    0.50
     gewährle
    0.49
    فاض
    0.49
    Sanchez
    0.47
    Lifecycle
    0.47
    Carlton
    0.47
    Rated
    0.46
    𝑭
    0.46
    Smile
    0.46
    ისუფ
    0.45
    POSITIVE LOGITS
    ının
    0.50
     Rails
    0.49
    <0x94>
    0.48
     to
    0.48
     destiné
    0.46
     P
    0.46
     onto
    0.45
     toward
    0.44
     Xiang
    0.44
     आग
    0.44
    Activations Density 0.000%

    No Known Activations