© 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. 16827
    Prev
    Next
    INDEX
    Explanations

    specific concepts and their contexts

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

    providing support, slightly nervous

    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
    حق
    0.53
     eigener
    0.50
    দা
    0.49
    >[</
    0.47
    നായി
    0.47
    akl
    0.47
     gegründet
    0.46
    داع
    0.46
     pensato
    0.45
     después
    0.45
    POSITIVE LOGITS
    sthe
    0.53
    -
    0.53
    ham
    0.50
    やま
    0.50
    細胞
    0.49
    鯰
    0.49
     OCEAN
    0.48
     Cruises
    0.47
    umn
    0.47
     Deer
    0.46
    Activations Density 0.000%

    No Known Activations