© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 33924
    Prev
    Next
    INDEX
    Explanations

    hard to

    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_16_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
     κά
    0.83
    م
    0.77
     Brava
    0.73
    ன்
    0.70
    <unused2223>
    0.68
    adients
    0.67
    м
    0.67
    ק
    0.66
     Justiça
    0.66
    mittent
    0.66
    POSITIVE LOGITS
    in
    0.72
     tow
    0.70
     teha
    0.70
     to
    0.70
    "]
    0.69
     creates
    0.68
    ha
    0.68
    to
    0.67
    。
    0.67
    }
    0.64
    Activations Density 0.001%

    No Known Activations