© 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. 137220
    Prev
    Next
    INDEX
    Explanations

    College Cup

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

    trading signals and language

    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
     вз
    0.59
    時
    0.52
     времен
    0.51
     след
    0.50
     чи
    0.46
     n
    0.46
     доб
    0.46
     спа
    0.45
     нов
    0.45
     те
    0.45
    POSITIVE LOGITS
    >>(
    0.51
     Berl
    0.49
    不同的
    0.48
    aidl
    0.46
    براین
    0.46
    نتی
    0.45
     الاد
    0.45
    ΙΚ
    0.45
    HAEL
    0.45
    ▋
    0.44
    Activations Density 0.000%

    No Known Activations