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

    Neuronpedia

    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. 45596
    Prev
    Next
    INDEX
    Explanations

    knight

    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
    </h3>
    0.73
    UN
    0.65
    </i>
    0.63
    -
    0.63
    UNE
    0.58
    ickets
    0.54
    ae
    0.54
    </h6>
    0.53
    -"
    0.52
     Sykes
    0.52
    POSITIVE LOGITS
     chival
    0.67
     investigador
    0.60
     службы
    0.59
    ኚ
    0.59
    rider
    0.58
    రణ
    0.58
    ैनिक
    0.57
    ضي
    0.57
    𝓖
    0.57
    %，
    0.57
    Activations Density 0.011%

    No Known Activations