© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 212299
    Prev
    Next
    INDEX
    Explanations

    data types 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-it/resid_post/layer_40_width_262k_l0_medium
    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
     salicylic
    0.48
    akova
    0.46
     gradi
    0.46
     *@
    0.44
    ۝
    0.42
    ிருந்தார்
    0.42
    য়াস
    0.41
    玨
    0.40
    lightbox
    0.40
     nitride
    0.40
    POSITIVE LOGITS
    Loc
    0.45
    CSS
    0.43
    ↵
    0.40
    {{
    0.40
    ader
    0.39
    CN
    0.39
    loc
    0.39
    CS
    0.38
    GB
    0.38
    IG
    0.37
    Activations Density 0.002%

    No Known Activations