© 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-65K
    7. 51049
    Prev
    Next
    INDEX
    Explanations

    criminal history, selling, revenue, statistics

    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
    টেন
    0.53
    тров
    0.50
    deviceName
    0.49
    studentRecord
    0.48
    つもり
    0.48
    Ꮵ
    0.48
    шот
    0.48
    Ҭ
    0.48
    destroyEach
    0.47
    位数
    0.47
    POSITIVE LOGITS
     a
    0.50
     DESIGN
    0.46
    able
    0.46
     Design
    0.45
     API
    0.45
    il
    0.45
     developers
    0.44
     CM
    0.44
     IA
    0.44
     Consider
    0.43
    Activations Density 0.001%

    No Known Activations