© 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. 40491
    Prev
    Next
    INDEX
    Explanations

    1 million, 1 billion

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

    numbers following '1'

    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
    k
    0.54
    0
    0.50
     hundred
    0.46
     dozen
    0.46
    i
    0.46
     A
    0.45
     H
    0.44
     Cali
    0.44
    ０
    0.43
    t
    0.42
    POSITIVE LOGITS
    Drawable
    0.50
    Neigh
    0.49
    Navbar
    0.46
    绎
    0.46
    Cliente
    0.45
     लीजिएगा
    0.45
    UnderTest
    0.45
    硋
    0.45
    PMorgan
    0.45
    𒊏
    0.45
    Activations Density 0.010%

    No Known Activations