© 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. 174377
    Prev
    Next
    INDEX
    Explanations

    in or about

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

    question text

    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
     ውሃ
    0.51
     localVar
    0.50
     తెలిపారు
    0.48
     dispersive
    0.48
     longitudinal
    0.46
     ።
    0.46
    <unused1798>
    0.46
    <unused1097>
    0.45
    netHex
    0.45
    ası
    0.44
    POSITIVE LOGITS
    攫
    0.46
    淥
    0.46
    iope
    0.46
    踴
    0.46
    蘄
    0.45
     innoc
    0.45
    جاد
    0.45
    ض
    0.44
     OWN
    0.44
    拈
    0.43
    Activations Density 0.001%

    No Known Activations