© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8372
    Prev
    Next
    INDEX
    Explanations

    specific technical terms

    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
    ਨ
    1.56
    an
    1.48
    요
    1.35
    in
    1.33
    ہ
    1.31
    नाडु
    1.23
     leaned
    1.22
    homme
    1.22
    at
    1.21
    ه
    1.17
    POSITIVE LOGITS
     demographics
    1.24
     Pennsylvania
    1.15
    ضو
    1.12
     sensory
    1.07
    𝘱
    1.05
     occupants
    1.04
     pixels
    1.04
     Benchmark
    1.04
    複数の
    1.03
    ANDA
    1.02
    Activations Density 0.000%

    No Known Activations