© 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. 3651
    Prev
    Next
    INDEX
    Explanations

    guaranteed path

    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
    فاع
    0.96
    izacji
    0.95
    izie
    0.88
    环境中
    0.86
    ë
    0.86
    搆
    0.85
    ime
    0.85
     masker
    0.85
    angani
    0.84
     klien
    0.84
    POSITIVE LOGITS
     listed
    1.34
     interesting
    1.29
     advertised
    1.28
     admirable
    1.22
     sticker
    1.22
     Advert
    1.20
     LQ
    1.19
     Lore
    1.19
    字
    1.19
     pn
    1.19
    Activations Density 0.017%

    No Known Activations