© 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. 204274
    Prev
    Next
    INDEX
    Explanations

    Samsung camp

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

    generation, projectile, within

    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
     புத்த
    0.57
    ხ
    0.56
     بغیر
    0.51
     cabelos
    0.47
     diariamente
    0.46
     profesores
    0.46
     yaşanan
    0.45
     bilgiler
    0.45
    Hight
    0.45
     Deportivo
    0.44
    POSITIVE LOGITS
    0.44
     мэ
    0.42
     좀
    0.41
    ovať
    0.41
     tasks
    0.41
    цыі
    0.41
    BUT
    0.41
    )
    0.39
     allocations
    0.39
     bounds
    0.39
    Activations Density 0.001%

    No Known Activations