© 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. 77060
    Prev
    Next
    INDEX
    Explanations

    KEYLESS START

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

    ranking numbers and symbols

    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
    初期
    0.36
    おく
    0.35
    thrown
    0.35
    ジェル
    0.35
    μέν
    0.35
    ´
    0.35
     pula
    0.34
    Pale
    0.34
    ˛
    0.34
    Initial
    0.34
    POSITIVE LOGITS
     segundo
    0.44
     второго
    0.41
     δεύτε
    0.40
    来越
    0.40
    bindingNavigator
    0.39
     sustancias
    0.39
     zuletzt
    0.39
    ອງ
    0.39
     respectivamente
    0.38
     ຮ
    0.38
    Activations Density 0.046%

    No Known Activations