© 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. 191534
    Prev
    Next
    INDEX
    Explanations

    own special

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

    countries and locations

    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
     quenched
    0.47
    P
    0.46
    inins
    0.46
    ওর
    0.44
     Ionic
    0.44
    ffekt
    0.43
     फंड
    0.43
    jats
    0.43
    Antae
    0.43
     Quaternion
    0.42
    POSITIVE LOGITS
     mercanc
    0.42
     최고의
    0.41
     mempunyai
    0.40
     muchos
    0.40
     نے
    0.39
     તે
    0.39
    浒
    0.39
     весь
    0.39
     már
    0.39
     vendita
    0.39
    Activations Density 0.000%

    No Known Activations