© 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. 44305
    Prev
    Next
    INDEX
    Explanations

    prohibition

    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
     اﻻ
    1.27
    不過
    1.25
    צ
    1.25
     Бі
    1.23
    항공
    1.19
    스
    1.19
    при
    1.18
     मूल्यांकन
    1.18
     일
    1.16
     خوبی
    1.16
    POSITIVE LOGITS
    speople
    1.23
    soever
    1.11
    tım
    1.08
    '
    1.07
    jacoco
    1.06
    larıyla
    1.05
    metic
    1.04
    Y
    1.02
    Im
    1.01
    tober
    1.01
    Activations Density 0.000%

    No Known Activations