© 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. 17-GEMMASCOPE-2-RES-16K
    7. 2145
    Prev
    Next
    INDEX
    Explanations

    rewards and benefits

    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_17_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
    νας
    1.06
     সৈয়দ
    0.98
    disturbance
    0.97
    훤
    0.94
     leisurely
    0.93
    जिट
    0.93
    entery
    0.90
     footh
    0.88
     랜
    0.88
    রেক
    0.87
    POSITIVE LOGITS
     seekers
    1.30
    幅度
    1.20
    制度
    1.11
     seeker
    1.07
    seekers
    1.06
     স্বরূপ
    1.04
     Offered
    1.03
    giver
    1.03
    স্বরূপ
    1.02
    seeker
    1.00
    Activations Density 0.577%

    No Known Activations