© 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-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8648
    Prev
    Next
    INDEX
    Explanations

    Visit + proper nouns or specific things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jl
    0.42
     humid
    0.42
     DQN
    0.41
    afka
    0.41
    }{\
    0.41
    >${
    0.40
    humidity
    0.40
    混沌
    0.40
     cha
    0.40
     humidity
    0.40
    POSITIVE LOGITS
     Guyana
    0.68
     artiste
    0.61
    🏾
    0.57
     artistes
    0.55
    🏿
    0.54
    artiste
    0.53
     tassa
    0.53
     Programmes
    0.53
     Labour
    0.52
     Programme
    0.52
    Activations Density 0.002%

    No Known Activations