© 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. 221916
    Prev
    Next
    INDEX
    Explanations

    different languages and conjunctions

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

    multiple conjunctions and connections

    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
    ิ
    0.48
     serien
    0.46
     Gemä
    0.46
    デビュー
    0.45
    در
    0.44
    ัต
    0.43
     Schönheit
    0.43
    Producto
    0.42
    ำ
    0.42
     triunfo
    0.42
    POSITIVE LOGITS
     và
    0.56
     ಮತ್ತು
    0.55
    性和
    0.55
     και
    0.54
     ਅਤੇ
    0.54
     এবং
    0.52
     અને
    0.52
     videocon
    0.52
     மற்றும்
    0.51
     және
    0.50
    Activations Density 0.001%

    No Known Activations