© 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. 164435
    Prev
    Next
    INDEX
    Explanations

    ’s also there free mobile guide

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

    measurement units like kcal

    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
     नाइ
    0.51
    נ
    0.49
    ブーツ
    0.48
    酴
    0.47
     או
    0.46
    Articulation
    0.46
    inburgh
    0.46
    нения
    0.46
     ブーツ
    0.45
     Dolls
    0.45
    POSITIVE LOGITS
    ’
    0.56
    s
    0.52
    self
    0.45
     accepté
    0.44
    getCurrent
    0.43
    好了
    0.43
     appartiennent
    0.42
    회
    0.42
    星
    0.42
    acceptance
    0.42
    Activations Density 0.000%

    No Known Activations