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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 8613
    Prev
    Next
    INDEX
    Explanations

    calculating differences and ratios

    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_all/layer_41_width_262k_l0_big
    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
    }=\{\
    0.39
     agacch
    0.39
     неприят
    0.39
    ဝ
    0.38
     implementar
    0.38
    㫙
    0.37
    抺
    0.37
    agamanam
    0.37
     구현
    0.37
     vudd
    0.37
    POSITIVE LOGITS
     calculation
    0.55
     Calculation
    0.51
    calculation
    0.50
    Calculation
    0.47
    0.46
     calculations
    0.45
     Calculations
    0.44
     calculated
    0.41
    calculations
    0.41
    9
    0.41
    Activations Density 0.003%

    No Known Activations