© 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. 245926
    Prev
    Next
    INDEX
    Explanations

    founder of / like others

    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
    idered
    0.47
     impedances
    0.44
    hiddenMap
    0.44
    QFont
    0.44
    ┣
    0.44
     imprison
    0.43
    ारे
    0.42
     oppression
    0.42
    dimensioni
    0.42
    वारे
    0.41
    POSITIVE LOGITS
     Cheek
    0.54
     Ted
    0.53
    égek
    0.53
     a
    0.52
     Tar
    0.52
     Thom
    0.51
     Lets
    0.51
     Author
    0.50
     Coordinator
    0.50
     Bonus
    0.50
    Activations Density 0.000%

    No Known Activations