© 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. 81396
    Prev
    Next
    INDEX
    Explanations

    publishing company, to carry, or decide

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

    single music

    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
     Denise
    0.42
     relief
    0.42
     veilig
    0.41
     in
    0.41
    رائی
    0.40
    莅
    0.40
     قالت
    0.40
    accueil
    0.39
     deux
    0.38
     Sicherheit
    0.38
    POSITIVE LOGITS
     intoler
    0.48
     аген
    0.48
     मंजूर
    0.48
     atributos
    0.46
     uncountable
    0.46
    рыма
    0.46
    íduos
    0.45
    =',
    0.45
     noches
    0.45
     अमाव
    0.45
    Activations Density 0.000%

    No Known Activations