© 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. 197397
    Prev
    Next
    INDEX
    Explanations

    New Zealand art

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

    social anxiety and offering 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
    Ꮁ
    0.47
    雯
    0.46
    ShaderType
    0.45
    ETERS
    0.45
     कहें
    0.43
    जनबी
    0.43
    STRACT
    0.41
    σης
    0.41
    วิ่ง
    0.41
    BURSE
    0.41
    POSITIVE LOGITS
     transformative
    0.47
     técn
    0.46
     indeterminate
    0.46
     Biennale
    0.46
     Ó
    0.44
     underwhelming
    0.44
    onders
    0.44
    ersi
    0.44
     ATA
    0.43
    ordre
    0.42
    Activations Density 0.000%

    No Known Activations