© 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. 28956
    Prev
    Next
    INDEX
    Explanations

    foreign language terms

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

    harvests, vacation, bloom, Domain

    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
     Balancing
    0.41
    Filename
    0.39
     والمر
    0.39
     filenames
    0.39
    Analytics
    0.39
    Hal
    0.38
     Bal
    0.38
    @@]
    0.38
    洺
    0.38
    جه
    0.37
    POSITIVE LOGITS
     bios
    0.46
    minen
    0.45
    殃
    0.43
     perlu
    0.43
    pleri
    0.43
     blamed
    0.43
    pesar
    0.43
     reliant
    0.42
     envolv
    0.41
    bios
    0.41
    Activations Density 0.000%

    No Known Activations