© 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. 117442
    Prev
    Next
    INDEX
    Explanations

    by or main characteristics

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

    Key rank, covers broken

    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
     Gum
    0.43
    sort
    0.42
    沉
    0.41
    ALL
    0.41
    bg
    0.40
    omens
    0.40
    anganan
    0.39
    definitions
    0.39
    dir
    0.39
    Gum
    0.38
    POSITIVE LOGITS
     aprile
    0.59
     llevará
    0.54
     infield
    0.52
     pręd
    0.50
     ၂
    0.50
     testicule
    0.50
     ক্রমাগত
    0.49
     ntawm
    0.49
    Jähr
    0.49
     cál
    0.49
    Activations Density 0.000%

    No Known Activations