© 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. 53868
    Prev
    Next
    INDEX
    Explanations

    tell us

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

    conveying implication or emphasis

    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
    ENIDO
    0.47
    เลือก
    0.45
    発
    0.44
    மை
    0.42
    隷
    0.42
    EL
    0.42
    IDAD
    0.41
    キャリア
    0.41
    援助
    0.41
    ע
    0.40
    POSITIVE LOGITS
    bmp
    0.52
    attro
    0.52
     jeden
    0.52
    (){
    0.51
    arter
    0.50
     ();
    0.49
     leb
    0.48
    odt
    0.48
     etik
    0.47
    bein
    0.47
    Activations Density 0.000%

    No Known Activations