© 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-65K
    7. 4761
    Prev
    Next
    INDEX
    Explanations

    substitution, replacement, or code symbols

    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_65k_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
    ió
    1.22
    agricult
    1.11
     $<$
    1.10
     $(<
    1.06
    რე
    1.05
     Reforma
    1.04
    embod
    1.02
    ians
    1.01
    anil
    1.01
    ⚭
    1.01
    POSITIVE LOGITS
    する
    1.14
    т
    1.10
    한다는
    1.06
     한다는
    1.06
    らう
    1.03
     favourite
    1.02
     perfectly
    1.01
    することができます
    1.01
    明顯
    1.01
    無法
    1.00
    Activations Density 0.004%

    No Known Activations