© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 105062
    Prev
    Next
    INDEX
    Explanations

    foreign language or topic

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

    HDR support

    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
    King
    0.51
    Trial
    0.49
    Proof
    0.46
    Pay
    0.46
    Drawer
    0.46
    Third
    0.45
    Children
    0.44
    리
    0.44
    Pro
    0.44
    Calendar
    0.44
    POSITIVE LOGITS
     ليس
    0.55
     iguais
    0.53
     concor
    0.51
     konkur
    0.50
     konkurs
    0.50
    ahassee
    0.50
     previsto
    0.49
     भाजप
    0.49
     potrebbero
    0.49
    kt
    0.48
    Activations Density 0.000%

    No Known Activations