© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 191545
    Prev
    Next
    INDEX
    Explanations

    product, app, text, history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
    ImageList
    0.48
    竰
    0.45
     অংশগ্রহ
    0.44
    imageList
    0.41
    िज्या
    0.40
    မဲ့
    0.40
     preschool
    0.40
    🦴
    0.39
    udarstvennyj
    0.38
    選舉
    0.38
    POSITIVE LOGITS
     Tafel
    0.40
     Subsec
    0.39
     ríos
    0.38
     null
    0.37
    unning
    0.37
    adeo
    0.36
    Though
    0.36
     foul
    0.35
     Reno
    0.35
    reno
    0.35
    Activations Density 0.000%

    No Known Activations