© 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. 44246
    Prev
    Next
    INDEX
    Explanations

    towels and bed linen included

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

    phrase validation

    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
    is
    0.49
    s
    0.45
     plaus
    0.45
    agor
    0.44
    primer
    0.43
     pares
    0.42
    ur
    0.42
    gdx
    0.42
    ల
    0.41
    Петер
    0.41
    POSITIVE LOGITS
    мом
    0.48
     &/
    0.46
     '':
    0.45
    済
    0.45
     Võ
    0.44
    іга
    0.42
     достат
    0.41
    可能です
    0.41
     зберіга
    0.41
     badges
    0.41
    Activations Density 0.000%

    No Known Activations