© 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. 40-GEMMASCOPE-2-RES-262K
    7. 34071
    Prev
    Next
    INDEX
    Explanations

    body, parameters, github, Autom

    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
    䅡
    0.40
     Breton
    0.40
     gaf
    0.38
    ga
    0.38
     Arthur
    0.37
     mirror
    0.36
    ajax
    0.35
    lateral
    0.35
    ጋ
    0.35
     Ga
    0.35
    POSITIVE LOGITS
    ()'
    0.43
    toml
    0.42
     Transforming
    0.41
    tolower
    0.41
    តិ
    0.39
     Paying
    0.39
    犇
    0.39
    ToJson
    0.38
    ObjectUnderTest
    0.38
    abetes
    0.38
    Activations Density 0.004%

    No Known Activations