© 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. 2409
    Prev
    Next
    INDEX
    Explanations

    [placeholder name, if known, otherwise use title]

    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
     agrup
    0.42
    IFORN
    0.41
     tergantung
    0.41
     propriedades
    0.40
     conformidad
    0.40
     diffusivity
    0.40
    .(*
    0.39
    ᚖ
    0.39
     interfering
    0.39
     carbure
    0.39
    POSITIVE LOGITS
     Leadership
    0.56
     Unavailable
    0.52
     Research
    0.50
    gender
    0.49
     LinkedIn
    0.49
     Otherwise
    0.48
     Addressing
    0.47
     Director
    0.47
     Gender
    0.47
     Receiving
    0.46
    Activations Density 0.001%

    No Known Activations