© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 41802
    Prev
    Next
    INDEX
    Explanations

    media titles and names

    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
     Compile
    1.08
     absenteeism
    1.07
     oranges
    0.98
    логи
    0.98
     delimiters
    0.96
    ρες
    0.94
    ेक्षा
    0.92
    ﻚ
    0.91
     beginnings
    0.90
     shrinks
    0.89
    POSITIVE LOGITS
    ı
    1.13
    ิง
    1.12
    ка
    1.09
    ف
    1.04
     hasn
    1.01
     można
    0.99
     voidaan
    0.98
    드
    0.96
    িত্ব
    0.95
     ສະ
    0.94
    Activations Density 0.011%

    No Known Activations