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. 22-GEMMASCOPE-2-RES-16K
    4. 9098
    Prev
    Next
    INDEX
    Explanations

    minimum thresholds

    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_22_width_16k_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
     puncak
    1.08
    election
    1.06
     motivo
    0.96
    다
    0.95
    ன்
    0.93
    outed
    0.93
     asunto
    0.90
    rini
    0.90
    र
    0.89
    ಜು
    0.89
    POSITIVE LOGITS
     viable
    1.28
     detectable
    1.22
     acceptable
    1.11
    acceptable
    1.03
     reproducible
    1.02
     wage
    1.02
     betre
    1.02
     Wage
    1.01
     requirement
    0.99
    ists
    0.98
    Activations Density 0.058%

    No Known Activations