© 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. 3129
    Prev
    Next
    INDEX
    Explanations

    i think

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

    expressing belief or assumption

    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
     morphisms
    0.25
     अथवा
    0.25
     किंवा
    0.22
    ，
    0.22
    )،
    0.22
     व
    0.21
    ){
    0.21
    および
    0.21
    و
    0.21
    ،
    0.21
    POSITIVE LOGITS
     there
    0.31
     it
    0.31
     they
    0.28
     તેઓ
    0.25
     هناك
    0.25
     we
    0.25
     everyone
    0.23
    there
    0.23
    ئة
    0.23
     الحكومة
    0.23
    Activations Density 0.633%

    No Known Activations