© 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-65K
    7. 54076
    Prev
    Next
    INDEX
    Explanations

    network effects or higher repetition

    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_65k_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
     roux
    0.46
    a
    0.45
    Pri
    0.44
    ه
    0.44
    consent
    0.44
    商家
    0.44
    iul
    0.43
    া
    0.41
    ジョン
    0.41
    扉
    0.40
    POSITIVE LOGITS
     بعد
    0.49
     लिख
    0.49
     بط
    0.49
     봐야
    0.47
     ശക്തി
    0.47
     declar
    0.46
     scares
    0.45
     declarar
    0.45
    𒂵
    0.45
     numero
    0.45
    Activations Density 0.001%

    No Known Activations