© 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. 40-GEMMASCOPE-2-RES-262K
    7. 110736
    Prev
    Next
    INDEX
    Explanations

    tensor dimensions and operations

    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
    摞
    0.47
    rows
    0.42
    ரோ
    0.40
     admissions
    0.40
    sample
    0.40
     sample
    0.39
    anzen
    0.39
     Admissions
    0.39
    គោ
    0.39
     Rowe
    0.38
    POSITIVE LOGITS
     dim
    0.45
    (-
    0.43
     =-
    0.41
    },-
    0.41
    =-
    0.40
     Dim
    0.40
    Dim
    0.39
    }(-
    0.39
    딤
    0.39
     Soud
    0.38
    Activations Density 0.003%

    No Known Activations