© 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. 209430
    Prev
    Next
    INDEX
    Explanations

    leave it, olive oil, needed to

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

    technical report

    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
    cash
    0.56
    es
    0.53
    Fashion
    0.51
    Mah
    0.51
    Cash
    0.49
    versation
    0.49
    ॅ
    0.49
    efficacy
    0.46
    Ys
    0.46
    ে
    0.45
    POSITIVE LOGITS
     translateX
    0.44
     vuelo
    0.44
     ido
    0.44
     gyroscope
    0.44
     univariate
    0.43
     chron
    0.43
     spoj
    0.43
     extractive
    0.43
    洛
    0.43
     zenith
    0.42
    Activations Density 0.000%

    No Known Activations