© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200493
    Prev
    Next
    INDEX
    Explanations

    political positions and succession

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific and technical descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     забезпе
    0.66
    いますが
    0.54
     обеспечивает
    0.53
     construcción
    0.52
    쿨
    0.49
     우리가
    0.49
     그대로
    0.48
     galvanometer
    0.46
     válvula
    0.45
    чної
    0.44
    POSITIVE LOGITS
    a
    0.48
     There
    0.48
    u
    0.48
     Each
    0.46
     Reach
    0.43
     Ses
    0.43
    There
    0.41
     falt
    0.41
     suspicions
    0.41
    Swipe
    0.40
    Activations Density 0.001%

    No Known Activations