© 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. 4905
    Prev
    Next
    INDEX
    Explanations

    specific entities and concepts

    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
    ڑے
    0.53
    medieval
    0.52
    انوي
    0.50
    മാ
    0.49
    غذ
    0.49
    ীপ
    0.48
    NUCLEAR
    0.48
    ച
    0.48
    нача
    0.48
    <0xA3>
    0.47
    POSITIVE LOGITS
    -
    0.54
    6
    0.52
    3
    0.50
    :
    0.47
    er
    0.46
     முன்ப
    0.46
    rom
    0.46
     het
    0.46
     enda
    0.45
    ruiter
    0.45
    Activations Density 0.001%

    No Known Activations