© 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. 233288
    Prev
    Next
    INDEX
    Explanations

    promete/proclaimed/proclaims

    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
    }^{+}=
    0.59
    cian
    0.47
     ACLU
    0.47
     COM
    0.47
    determin
    0.46
    rsi
    0.46
     USS
    0.46
     NAACP
    0.45
     ش
    0.45
    plural
    0.45
    POSITIVE LOGITS
     promete
    0.50
    ДУ
    0.50
    маты
    0.49
     epitope
    0.49
     proclaimed
    0.47
    过的
    0.46
     loopt
    0.45
    ơ
    0.45
    ightly
    0.45
     proclaims
    0.45
    Activations Density 0.000%

    No Known Activations