Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31218
    Prev
    Next
    INDEX
    Explanations

    package main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     minded
    1.04
    ット
    0.96
    л
    0.95
    ঁজ
    0.87
     hWnd
    0.86
     marbled
    0.86
     ethereal
    0.85
     hemp
    0.84
    日
    0.83
     synthes
    0.82
    POSITIVE LOGITS
    larında
    1.20
    iances
    1.16
    ine
    1.09
    ع
    1.09
    ic
    1.05
    사항
    1.05
    頗
    1.05
    roscopy
    1.04
    علم
    1.04
    醫
    1.03
    Activations Density 0.001%

    No Known Activations