© 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. 10319
    Prev
    Next
    INDEX
    Explanations

    risk assessment factors

    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
    辙
    0.90
     rhythms
    0.88
    乾燥
    0.88
    drying
    0.87
    dequeue
    0.87
    рих
    0.85
     যায়
    0.85
     Dynamical
    0.84
    乾
    0.83
     jig
    0.83
    POSITIVE LOGITS
     appetite
    1.27
     reward
    1.24
     Appetite
    1.21
    ier
    1.20
     aversion
    1.19
     assessment
    1.12
     Reward
    1.10
    reward
    1.10
     appet
    1.07
     averse
    1.06
    Activations Density 0.053%

    No Known Activations