© 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. 31-GEMMASCOPE-2-RES-262K
    7. 52436
    Prev
    Next
    INDEX
    Explanations

    describing context and qualifiers

    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
    A
    0.45
     findings
    0.43
    Message
    0.42
    ]'
    0.42
     Collider
    0.41
     etc
    0.41
     ([
    0.41
     results
    0.40
    AIDS
    0.40
     [
    0.40
    POSITIVE LOGITS
    idze
    0.52
    ὴν
    0.47
    íce
    0.46
    呂
    0.45
    萬元
    0.44
    тися
    0.44
    मानस
    0.44
    ुए
    0.44
     低
    0.43
     fester
    0.43
    Activations Density 0.002%

    No Known Activations