© 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. 40-GEMMASCOPE-2-RES-65K
    7. 3170
    Prev
    Next
    INDEX
    Explanations

    by default

    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_65k_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
    м
    0.55
    ↵
    0.52
    م
    0.49
    ר
    0.45
    }$}
    0.45
    ن
    0.44
    ன்
    0.44
    e
    0.44
    uable
    0.42
    】
    0.42
    POSITIVE LOGITS
     virtue
    1.13
     dint
    0.88
    zantine
    0.88
     means
    0.70
    衷
    0.67
     separado
    0.64
     way
    0.61
     mistake
    0.61
     conséquent
    0.60
    products
    0.60
    Activations Density 0.156%

    No Known Activations