© 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. 194147
    Prev
    Next
    INDEX
    Explanations

    relativeabsolute skill

    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
     "",
    0.48
     kit
    0.44
    ({},
    0.43
     fiecare
    0.42
     (),
    0.41
     '',
    0.41
    kit
    0.40
     &,
    0.39
     {},
    0.38
     optimized
    0.38
    POSITIVE LOGITS
    掬
    0.48
     docente
    0.41
    たとえば
    0.41
    認為
    0.41
    Midnight
    0.41
    ᱓
    0.40
    教师
    0.40
    whose
    0.40
    㳑
    0.40
     যেত
    0.39
    Activations Density 0.001%

    No Known Activations