© 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. 12936
    Prev
    Next
    INDEX
    Explanations

    more detailed

    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
    u
    2.42
    ANGE
    2.41
    zego
    2.33
    ου
    2.31
    慮
    2.31
    ್ಣ
    2.26
    ος
    2.24
    هل
    2.18
    ׁ
    2.18
    色列
    2.14
    POSITIVE LOGITS
    ly
    2.55
    nbsp
    2.46
    mente
    2.43
    mdash
    2.42
    <bos>
    2.27
    hellip
    2.24
    勬
    2.20
    instruction
    2.19
    middot
    2.17
    Leggi
    2.16
    Activations Density 0.014%

    No Known Activations