© 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. 31-GEMMASCOPE-2-RES-262K
    7. 125835
    Prev
    Next
    INDEX
    Explanations

    add the fractions, political activist, position bias

    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_31_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
    rés
    0.49
    your
    0.49
    ou
    0.47
    it
    0.46
    path
    0.46
    蹿
    0.46
    out
    0.45
    url
    0.44
    它的
    0.43
    është
    0.42
    POSITIVE LOGITS
     glTex
    0.42
     συγκεκρι
    0.42
     carcinomas
    0.41
     Differ
    0.40
    畚
    0.40
    เศษ
    0.39
     açısından
    0.39
     вмі
    0.38
    bindingFields
    0.38
     διαφο
    0.38
    Activations Density 0.001%

    No Known Activations