© 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-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10160
    Prev
    Next
    INDEX
    Explanations

    MentalHealth.gov

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     capability
    1.00
    駈
    0.93
     capabilities
    0.90
     expertise
    0.89
     Capability
    0.86
     require
    0.85
     perceive
    0.84
     Alright
    0.83
     liquid
    0.82
     Capabilities
    0.82
    POSITIVE LOGITS
    pss
    0.92
     facing
    0.92
     tambien
    0.88
    မျ
    0.86
    also
    0.86
    ኣ
    0.86
    ங்களும்
    0.85
    ⛧
    0.85
    电线路
    0.84
     სახელმწიფო
    0.84
    Activations Density 0.009%

    No Known Activations