© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 113044
    Prev
    Next
    INDEX
    Explanations

    numbers, types, or code constructs

    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_31_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
    ር
    0.50
    फिर
    0.49
    hers
    0.48
    說
    0.47
    speeds
    0.46
    वर्ग
    0.46
    all
    0.46
    figs
    0.45
    olfo
    0.44
    }_{-}\
    0.44
    POSITIVE LOGITS
     supply
    0.57
     corrupted
    0.49
     supplying
    0.48
     monopol
    0.48
     Supply
    0.47
     providing
    0.47
     chapel
    0.47
     controversial
    0.47
     rainy
    0.47
    শোধ
    0.46
    Activations Density 0.000%

    No Known Activations