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. 7715
    Prev
    Next
    INDEX
    Explanations

    copyright notice and ownership

    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
    ت
    2.08
    ة
    1.94
    en
    1.82
    ת
    1.72
    ي
    1.64
    ourcen
    1.60
    quête
    1.57
    ంట్
    1.49
    ть
    1.48
    т
    1.47
    POSITIVE LOGITS
     možno
    1.42
    Charset
    1.36
    Như
    1.30
     nudity
    1.28
    Electricity
    1.26
    뺨
    1.25
    Fury
    1.25
    Handsome
    1.24
     contemplates
    1.23
    rus
    1.23
    Activations Density 0.000%

    No Known Activations