© 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. 121408
    Prev
    Next
    INDEX
    Explanations

    description of specific items

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

    pronoun followed by specific words

    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
     gates
    0.54
    आ
    0.53
     huts
    0.52
     importante
    0.50
    GATE
    0.50
     managers
    0.48
    hut
    0.48
    HA
    0.47
    हे
    0.47
    HI
    0.46
    POSITIVE LOGITS
    к
    0.51
     للس
    0.49
     Coupled
    0.49
     exerting
    0.47
     Pyr
    0.46
     Тео
    0.46
    怪
    0.46
     Cadastro
    0.45
     цу
    0.45
     விளங்க
    0.45
    Activations Density 0.000%

    No Known Activations