© 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. 3536
    Prev
    Next
    INDEX
    Explanations

    technical descriptions and listings

    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
     rém
    1.78
    ointees
    1.69
    生地
    1.65
    駅
    1.61
    꾀
    1.55
     nějak
    1.54
    providecommand
    1.52
    劲
    1.52
    [.
    1.51
     Destination
    1.50
    POSITIVE LOGITS
     interplay
    1.14
    avali
    1.10
     breakdown
    1.10
    独立的
    1.08
    катери
    1.06
     overview
    1.05
     review
    1.03
     interconnection
    1.00
     coexistence
    0.99
    葳
    0.97
    Activations Density 0.096%

    No Known Activations