© 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. 7-GEMMASCOPE-2-RES-16K
    7. 50
    Prev
    Next
    INDEX
    Explanations

    best quality choices

    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_7_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
    য়দ
    2.16
    ๖
    2.09
    ീയ
    2.07
    ৭০
    2.01
    Mia
    1.97
     natureza
    1.95
    số
    1.91
     trọng
    1.89
    rischen
    1.88
    ๗
    1.87
    POSITIVE LOGITS
     suited
    1.95
     restore
    1.80
     grasp
    1.75
    ोत्तर
    1.74
     quality
    1.73
     Quality
    1.73
     মানের
    1.70
     attribute
    1.70
     იყოს
    1.70
    يها
    1.68
    Activations Density 1.666%

    No Known Activations