© 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. 21475
    Prev
    Next
    INDEX
    Explanations

    distances and features

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

    risks, gaps, and adaptations

    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
     дополнительные
    0.46
     একজন
    0.43
    ⠀⠀
    0.42
    একজন
    0.42
     হয়েছে
    0.42
    или
    0.41
    磺
    0.41
    邂
    0.41
    ңа
    0.40
    篠
    0.40
    POSITIVE LOGITS
     critères
    0.56
     criteri
    0.47
    riteria
    0.46
     toil
    0.46
     Europe
    0.45
     hiver
    0.45
     déjà
    0.44
     whence
    0.44
     criter
    0.44
     hordes
    0.44
    Activations Density 0.000%

    No Known Activations