© 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. 14501
    Prev
    Next
    INDEX
    Explanations

    seed germination

    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
     alloc
    1.50
     overfitting
    1.50
    ignore
    1.48
    umis
    1.41
    utives
    1.40
     ecosystem
    1.37
    ylim
    1.37
    }%
    1.36
     xgboost
    1.34
    elih
    1.33
    POSITIVE LOGITS
    вара
    1.83
    נית
    1.59
     Mujer
    1.59
    ва
    1.55
    敵人
    1.52
    рный
    1.52
    كب
    1.50
     Mujeres
    1.47
    projectView
    1.47
    ሮ
    1.47
    Activations Density 0.047%

    No Known Activations