© 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. 771
    Prev
    Next
    INDEX
    Explanations

    microsoft.com/en-us/

    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
    ANDER
    1.27
    aan
    1.20
    ﻧ
    1.18
     courants
    1.12
    i
    1.12
    aa
    1.08
    هما
    1.05
    {
    1.05
    ла
    1.05
     Conspiracy
    1.04
    POSITIVE LOGITS
    ل
    1.55
    ка
    1.48
    К
    1.41
    stion
    1.23
     Zoho
    1.21
     শ্
    1.20
     новой
    1.19
    Я
    1.16
     xứng
    1.15
    竭
    1.15
    Activations Density 0.013%

    No Known Activations