© 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. 16-GEMMASCOPE-2-RES-262K
    7. 34518
    Prev
    Next
    INDEX
    Explanations

    Platooning, Frobenius norm, Wicca

    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
    c
    0.61
    l
    0.59
     mentale
    0.58
    麻煩
    0.58
    呐
    0.57
     se
    0.54
    lion
    0.54
     auff
    0.54
    m
    0.54
     on
    0.54
    POSITIVE LOGITS
    ]
    0.73
    0
    0.71
    ة
    0.65
    رک
    0.62
    ’)
    0.60
    ඖ
    0.59
    ०
    0.59
    icians
    0.58
    }
    0.57
     Insights
    0.55
    Activations Density 0.000%

    No Known Activations