© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2869
    Prev
    Next
    INDEX
    Explanations

    initial followed by event

    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
    शुदा
    2.83
    ][:
    2.83
    ylate
    2.77
     σ
    2.66
    generic
    2.64
    eda
    2.61
    Damn
    2.60
    μπο
    2.56
    ])),
    2.52
    ਸ਼
    2.48
    POSITIVE LOGITS
    er
    2.88
    اك
    2.80
    eros
    2.70
    리티
    2.56
    zata
    2.54
    ا
    2.53
    त्रेयी
    2.50
    গ্ন
    2.47
    ි
    2.43
    ان
    2.40
    Activations Density 0.089%

    No Known Activations