© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27424
    Prev
    Next
    INDEX
    Explanations

    programmed to be a safe and helpful AI

    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
    עת
    0.41
     პროგრამ
    0.41
    Prz
    0.41
    prz
    0.40
    kipun
    0.40
     प्रोड
    0.40
    ᴾ
    0.40
    個セット
    0.39
    CLK
    0.39
    <0xE1>
    0.38
    POSITIVE LOGITS
    лён
    0.37
     Bays
    0.37
    рети
    0.36
     Certainly
    0.35
     Belly
    0.34
    zął
    0.34
     thao
    0.34
    震
    0.34
    lə
    0.33
    0.33
    Activations Density 0.090%

    No Known Activations