© 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. 8196
    Prev
    Next
    INDEX
    Explanations

    sports scoring and chess tactics

    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
    ViewPager
    0.35
     যেদিন
    0.31
    uité
    0.31
    从业
    0.30
    用户
    0.30
     Login
    0.30
     coprime
    0.29
    颉
    0.29
    订阅
    0.29
    巅
    0.29
    POSITIVE LOGITS
     scoring
    0.52
     turnovers
    0.48
     score
    0.46
     scored
    0.45
     possessions
    0.44
     momentum
    0.43
     possession
    0.42
     advantage
    0.42
     shots
    0.42
    score
    0.41
    Activations Density 0.022%

    No Known Activations