© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 24509
    Prev
    Next
    INDEX
    Explanations

    tool usage instructions

    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
     tweeted
    0.43
    阻
    0.41
    ₲
    0.40
    Sue
    0.39
    Norman
    0.38
     Apartments
    0.38
    Cllr
    0.38
     Jab
    0.38
    Jab
    0.38
    侶
    0.37
    POSITIVE LOGITS
     zod
    0.41
    Repository
    0.38
    응
    0.37
    Repositories
    0.37
     repository
    0.36
     repositories
    0.36
    vens
    0.35
    repo
    0.35
    repository
    0.35
     prépuce
    0.35
    Activations Density 0.001%

    No Known Activations