© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 75447
    Prev
    Next
    INDEX
    Explanations

    Bob Marley, fact table, Cape Buffalo

    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
    Compiler
    0.53
    said
    0.50
    A
    0.50
    Rec
    0.49
    Mam
    0.44
    As
    0.44
    End
    0.42
    Mach
    0.42
    Tit
    0.42
    Brooks
    0.42
    POSITIVE LOGITS
    !:
    0.52
     हमे
    0.49
    !"));
    0.48
    ్ఞ
    0.48
     }}">
    0.47
     Dob
    0.46
     Mục
    0.46
     항
    0.46
     डिसेंबर
    0.45
    !</
    0.45
    Activations Density 0.002%

    No Known Activations