© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 138775
    Prev
    Next
    INDEX
    Explanations

    was taken, able to, left undisturbed

    np_acts-logits-general · gemini-2.5-flash-lite

    fine-tuning, detection, analysis, awareness

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Certificate
    0.44
    適切
    0.43
    IB
    0.41
    Tw
    0.41
    лә
    0.41
     Appreciation
    0.41
     зарегистри
    0.40
    埌
    0.39
     Certificate
    0.39
     twig
    0.39
    POSITIVE LOGITS
    hesus
    0.51
    ammens
    0.50
    agent
    0.49
    䏹
    0.49
    ಶಾ
    0.48
     hoo
    0.47
    asset
    0.47
     深
    0.47
     杯
    0.47
     방
    0.47
    Activations Density 0.000%

    No Known Activations