© 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. 107367
    Prev
    Next
    INDEX
    Explanations

    access routes, worrying about, simple living

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

    contact for [placeholder]

    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
    ")]
    0.46
    blico
    0.43
    yama
    0.42
    jumpa
    0.41
    모
    0.41
     allow
    0.40
    Aplic
    0.40
    確定
    0.40
     astrological
    0.40
    ႈ
    0.40
    POSITIVE LOGITS
     দশকের
    0.50
     salespeople
    0.47
    𒀝
    0.45
    тив
    0.45
    য়ের
    0.43
     первой
    0.43
    ﺱ
    0.43
    镌
    0.43
    িং
    0.43
     últimas
    0.43
    Activations Density 0.001%

    No Known Activations