© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 45268
    Prev
    Next
    INDEX
    Explanations

    known, recommended, introduced

    np_acts-logits-general · gemini-2.5-flash-lite

    haiku prompts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    돔
    0.45
    ggen
    0.44
    지의
    0.43
    合法
    0.43
     excitatory
    0.42
     harming
    0.41
     vesicles
    0.41
    чок
    0.41
    Kotlin
    0.40
    崠
    0.40
    POSITIVE LOGITS
     oyunc
    0.46
     कम्प
    0.46
     تحقی
    0.45
     mendatang
    0.44
     trademark
    0.44
     Trink
    0.44
     Aug
    0.43
     کمپیوٹر
    0.42
     tredje
    0.42
     trink
    0.41
    Activations Density 0.000%

    No Known Activations