© 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. 60151
    Prev
    Next
    INDEX
    Explanations

    laws, loss, ban, force

    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
    ield
    0.43
    Step
    0.43
    amana
    0.42
    Arch
    0.42
    Aurora
    0.42
    Jessica
    0.41
    郭
    0.41
    Advance
    0.40
     Pickup
    0.40
     سمت
    0.40
    POSITIVE LOGITS
     vodu
    0.55
     financement
    0.54
     voda
    0.53
     lactic
    0.51
     tubig
    0.50
     agua
    0.48
     Lactobacillus
    0.47
     caractère
    0.47
    徎
    0.47
    ন্ধে
    0.47
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.