Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7878
    Prev
    Next
    INDEX
    Explanations

    tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
    గా
    1.84
    ‌ای
    1.82
    ਕ
    1.63
    ای
    1.63
    ë
    1.58
    ﻥ
    1.56
    ها
    1.56
    ive
    1.51
    ly
    1.50
    로
    1.49
    POSITIVE LOGITS
    t
    3.28
    tion
    3.10
    tions
    3.03
    tive
    3.01
    d
    3.01
    tional
    2.91
    tin
    2.75
    tól
    2.64
    tio
    2.62
    smanship
    2.55
    Activations Density 0.098%

    No Known Activations