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. 7895
    Prev
    Next
    INDEX
    Explanations

    negative effects or charges

    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
    ,..
    1.43
     pabbaj
    1.27
    Р
    1.24
    ladies
    1.23
     $('
    1.23
     mAb
    1.23
    overset
    1.23
    ры
    1.21
    mediated
    1.21
    &:
    1.21
    POSITIVE LOGITS
     dispersive
    1.28
     Orbit
    1.20
     progressive
    1.17
     excit
    1.17
    cznego
    1.12
     excitatory
    1.12
    매
    1.11
     impure
    1.10
    മ
    1.08
     conspired
    1.08
    Activations Density 0.000%

    No Known Activations