© 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. 40-GEMMASCOPE-2-RES-262K
    7. 205674
    Prev
    Next
    INDEX
    Explanations

    understanding concepts and their context

    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
    stairs
    0.41
    Glenn
    0.40
     여기가
    0.39
    Recognition
    0.39
     Département
    0.38
    鰭
    0.38
     believed
    0.38
    NIK
    0.37
    ???
    0.37
    !!!!
    0.37
    POSITIVE LOGITS
     ಸಾಮಾ
    0.43
     numeral
    0.39
    objectId
    0.38
     тогда
    0.37
     annulus
    0.37
    条
    0.37
    operatively
    0.37
    POSTFIELDS
    0.37
     anon
    0.37
    xcscheme
    0.35
    Activations Density 0.000%

    No Known Activations