© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4355
    Prev
    Next
    INDEX
    Explanations

    software lifecycle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     sublim
    1.42
    6
    1.36
    7
    1.28
    Levi
    1.26
    rinsic
    1.25
     subjekt
    1.25
    ฺ
    1.22
    ٦
    1.18
    ๖
    1.18
     transduction
    1.17
    POSITIVE LOGITS
    ouncement
    1.77
    hill
    1.70
    finder
    1.65
    unct
    1.59
     announcements
    1.58
    asm
    1.54
     evidence
    1.53
     Announcements
    1.52
     Evidence
    1.50
     cinch
    1.49
    Activations Density 0.017%

    No Known Activations