© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75851
    Prev
    Next
    INDEX
    Explanations

    lists, below, intends

    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
    水の
    0.52
     nouvelles
    0.49
    ڈر
    0.49
     đảo
    0.47
     vanaf
    0.47
    晧
    0.47
    水を
    0.47
    厛
    0.46
    ሙሉ
    0.45
     incredible
    0.45
    POSITIVE LOGITS
    owers
    0.48
     peč
    0.43
    </b>
    0.41
    affee
    0.41
    lists
    0.40
    ape
    0.40
    MyShop
    0.39
     connectors
    0.39
    oben
    0.39
    ählt
    0.38
    Activations Density 0.000%

    No Known Activations