© 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. 194056
    Prev
    Next
    INDEX
    Explanations

    Policy Transparency

    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
     slams
    0.45
     contrasting
    0.42
     plumes
    0.42
     slamming
    0.41
     contrast
    0.40
    飩
    0.40
     indecent
    0.40
     vendor
    0.39
     committed
    0.39
     slam
    0.39
    POSITIVE LOGITS
    에서는
    0.46
    에서도
    0.40
    에서의
    0.39
     tecnológico
    0.38
    성의
    0.38
    ☾
    0.38
     دیر
    0.37
    では
    0.37
     subjectivity
    0.37
    ধিক
    0.37
    Activations Density 0.002%

    No Known Activations