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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 914
    Prev
    Next
    INDEX
    Explanations

    shift towards

    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
    ست
    1.97
    ن
    1.66
    í
    1.63
    ку
    1.57
    میر
    1.55
    า
    1.55
    ன
    1.51
    ्ड
    1.41
    ла
    1.41
    าค
    1.36
    POSITIVE LOGITS
    が生
    1.35
    이면
    1.30
    Само
    1.21
    이니까
    1.14
    적으로
    1.12
    ﻞ
    1.05
    은
    1.03
     potted
    1.02
    이기
    1.02
     fawn
    1.01
    Activations Density 0.003%

    No Known Activations