© 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. 39524
    Prev
    Next
    INDEX
    Explanations

    professionals and notable people

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

    terms sometimes followed by punctuation

    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
     S
    0.43
     M
    0.41
     C
    0.40
    :</
    0.38
     შეიძლება
    0.38
     אנחנו
    0.36
     देखना
    0.36
     TEX
    0.36
    났
    0.35
    S
    0.35
    POSITIVE LOGITS
     российского
    0.44
     provenant
    0.43
     stort
    0.43
    が登場
    0.42
     submodule
    0.41
     manzanas
    0.41
    InSection
    0.41
     součástí
    0.41
    วัติ
    0.40
    റ്റ്
    0.40
    Activations Density 0.001%

    No Known Activations