© 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. 16-GEMMASCOPE-2-RES-262K
    7. 140242
    Prev
    Next
    INDEX
    Explanations

    occult and builders

    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_16_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
    𝕖
    0.55
    scopic
    0.54
    feeding
    0.51
    accumulation
    0.51
    pins
    0.49
     Ñ
    0.48
    shore
    0.47
     냉
    0.47
    श्वर
    0.46
    thermal
    0.46
    POSITIVE LOGITS
    Compet
    0.50
     queries
    0.47
     Compet
    0.46
     क्रमांका
    0.45
     competit
    0.42
     funciones
    0.42
    +//
    0.42
     diarias
    0.41
    Beverungen
    0.41
     ranks
    0.41
    Activations Density 0.000%

    No Known Activations