© 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. 9880
    Prev
    Next
    INDEX
    Explanations

    attacking, defending, pressing

    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
     நாடுகளில்
    0.41
    Unlimited
    0.41
     Unlimited
    0.40
    地図
    0.39
     isotope
    0.39
     unlimited
    0.39
     इंस्ट
    0.38
    胭
    0.38
    URNIZOR
    0.38
    GaAs
    0.38
    POSITIVE LOGITS
     defensively
    0.90
     defensive
    0.86
     offensively
    0.82
     dominating
    0.80
     aggress
    0.80
     pressing
    0.79
     attacking
    0.79
     harassing
    0.79
     offensive
    0.76
     tempo
    0.76
    Activations Density 0.011%

    No Known Activations