© 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. 49512
    Prev
    Next
    INDEX
    Explanations

    To followed by verb

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

    descriptive adjectives and concepts

    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
     kinematic
    0.41
    ,
    0.39
     further
    0.38
     अपेक्षित
    0.38
     Chipotle
    0.38
     supporting
    0.38
     Sweeney
    0.37
     pály
    0.37
     arbejde
    0.37
     inhibit
    0.37
    POSITIVE LOGITS
    Paf
    0.48
    िड
    0.44
    ultipl
    0.44
     }=
    0.44
     ज्योग्राफी
    0.44
    faz
    0.44
    sab
    0.43
    MessageType
    0.43
    фри
    0.42
    ficha
    0.42
    Activations Density 0.000%

    No Known Activations