© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 111395
    Prev
    Next
    INDEX
    Explanations

    temporal concepts and errors

    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_31_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
    8
    0.55
    6
    0.53
    ៤
    0.51
    4
    0.51
    9
    0.47
    е
    0.44
    nament
    0.43
     維尼
    0.43
    5
    0.43
    7
    0.42
    POSITIVE LOGITS
     a
    0.47
     as
    0.46
     thơ
    0.45
     Acids
    0.44
     substances
    0.43
     Source
    0.43
     enzymes
    0.43
     Ах
    0.42
    欉
    0.42
     Molecules
    0.42
    Activations Density 0.010%

    No Known Activations