© 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. 227737
    Prev
    Next
    INDEX
    Explanations

    Slovakia here, local talent

    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
     muslim
    0.49
     strongest
    0.48
    Brasil
    0.46
     diput
    0.46
    ￱
    0.45
     apropi
    0.44
     favorit
    0.44
     unreasonably
    0.44
    प्रमुख
    0.43
    kušen
    0.43
    POSITIVE LOGITS
     आधे
    0.49
    зар
    0.47
     توڑ
    0.46
    ಲ್ಲು
    0.44
    യാണ്
    0.44
    儚
    0.43
    aliy
    0.42
    ્ર
    0.42
     visualizing
    0.42
    謄
    0.42
    Activations Density 0.000%

    No Known Activations