© 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. 128205
    Prev
    Next
    INDEX
    Explanations

    law enforcement exemption, industry growth, operating systems

    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
    ClearedBy
    0.51
    ঃ
    0.48
    دی
    0.46
     creș
    0.44
    CreateCharacter
    0.44
    یدی
    0.44
     ভিতর
    0.44
    Blur
    0.43
    thinmathspace
    0.43
    ونی
    0.42
    POSITIVE LOGITS
    RID
    0.44
     polym
    0.43
    IFORN
    0.43
    rization
    0.41
    َت
    0.40
    RIC
    0.40
    ଟ
    0.40
    ER
    0.40
    OSED
    0.40
     hielo
    0.39
    Activations Density 0.003%

    No Known Activations