© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12999
    Prev
    Next
    INDEX
    Explanations

    valley phrases and descriptions

    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
    lyde
    2.35
     pushed
    2.10
    取り寄せ
    2.07
    認為
    2.04
    DefinitionGroup
    2.01
     Milner
    1.99
    פול
    1.98
    抿
    1.97
    駛
    1.97
    LineEdit
    1.96
    POSITIVE LOGITS
    uu
    1.75
    elements
    1.71
     internet
    1.69
    unia
    1.67
    多个
    1.66
    illions
    1.66
     banyak
    1.65
     একাধিক
    1.64
    multiple
    1.64
    aan
    1.64
    Activations Density 0.097%

    No Known Activations