© 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. 223135
    Prev
    Next
    INDEX
    Explanations

    literal physical personal

    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
    စျေး
    0.44
     मलयालम
    0.43
     matemat
    0.42
    ရှား
    0.42
    YNAMICS
    0.41
    测试
    0.40
     जगा
    0.40
    놁
    0.40
    𝓷
    0.39
    テスト
    0.39
    POSITIVE LOGITS
    Literal
    0.49
    Physical
    0.45
    Personal
    0.44
     physical
    0.42
     Personal
    0.42
     Physical
    0.41
     Literal
    0.40
     literal
    0.40
    literal
    0.40
     körper
    0.38
    Activations Density 0.008%

    No Known Activations