© 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. 157957
    Prev
    Next
    INDEX
    Explanations

    false alarms

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

    splitting models or data

    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
    enio
    0.58
    håll
    0.49
    石头
    0.46
    ♋
    0.46
     Stones
    0.46
     Carriers
    0.45
     Sizes
    0.45
     Hemos
    0.44
     Fewer
    0.44
    絃
    0.43
    POSITIVE LOGITS
    Collin
    0.55
    Oral
    0.49
    Sunday
    0.48
     屋
    0.47
     inesper
    0.47
     divisão
    0.47
    Lear
    0.47
    Journal
    0.47
     неожидан
    0.47
     derr
    0.46
    Activations Density 0.000%

    No Known Activations