© 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. 65257
    Prev
    Next
    INDEX
    Explanations

    Blvd, Susana, ID, hydrogen

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

    suggests or implies direction/assessment

    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
    鳩
    0.49
    en
    0.49
    ó
    0.48
    Software
    0.46
     deploying
    0.45
     زوج
    0.45
    䯩
    0.44
     साझेदारी
    0.44
    聝
    0.44
     software
    0.44
    POSITIVE LOGITS
    বিশ
    0.54
     Pampl
    0.49
     Susana
    0.48
    ිර
    0.48
    အနေ
    0.48
     Inggris
    0.47
     Blvd
    0.45
     Khark
    0.45
    ນີ້
    0.45
    }")]
    0.44
    Activations Density 0.000%

    No Known Activations