© 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. 22-GEMMASCOPE-2-RES-262K
    7. 14765
    Prev
    Next
    INDEX
    Explanations

    situations, states, or goals

    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_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
     이거
    1.06
     Davos
    1.03
    Kids
    0.98
     Folks
    0.98
     てる
    0.97
     Banff
    0.96
     Brexit
    0.96
    ฯ
    0.95
    Brexit
    0.94
     regs
    0.92
    POSITIVE LOGITS
     detrimental
    1.14
     stereotypical
    1.12
     minimalistic
    1.05
     necessities
    1.03
     miscellaneous
    1.00
     desired
    1.00
     harmful
    1.00
     pleasurable
    0.99
     respective
    0.99
     sarcastic
    0.96
    Activations Density 0.007%

    No Known Activations