© 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. 216900
    Prev
    Next
    INDEX
    Explanations

    suspension, site, issues, necessary

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

    attitudes towards or nature of

    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
    ლი
    0.52
    FindingsResponse
    0.51
     инвести
    0.48
     странах
    0.47
    לי
    0.46
    ז
    0.46
     снаб
    0.46
    }^{(\
    0.45
    мель
    0.45
    рова
    0.45
    POSITIVE LOGITS
     database
    0.49
     architecture
    0.49
     traverse
    0.49
    ow
    0.48
     atau
    0.48
     cybersecurity
    0.48
     C
    0.47
     College
    0.47
    <0xAE>
    0.47
     TV
    0.47
    Activations Density 0.002%

    No Known Activations