© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5502
    Prev
    Next
    INDEX
    Explanations

    code blocks and function definitions

    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
    s
    1.30
    ों
    1.20
    ként
    1.17
    h
    1.17
    í
    1.16
    ările
    1.13
    ą
    1.11
    ‌ای
    1.10
    多い
    1.09
    一带
    1.09
    POSITIVE LOGITS
    с
    1.00
    শীল
    0.98
    т
    0.97
     afar
    0.96
    स
    0.93
     exacerbated
    0.93
    ﻪ
    0.89
     corroborated
    0.89
     illegitimate
    0.88
    з
    0.88
    Activations Density 0.252%

    No Known Activations