© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11171
    Prev
    Next
    INDEX
    Explanations

    some followed by options or resources

    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
    erate
    2.64
     λεπ
    2.21
    ileged
    2.19
     pojed
    2.17
    ཏ
    2.11
    백
    2.08
    背面
    2.03
    өп
    2.02
    ৌম
    1.98
    eras
    1.98
    POSITIVE LOGITS
    beeld
    2.26
     bientôt
    2.22
    xhtml
    2.21
    hi
    2.11
    ító
    2.08
     alimentación
    2.07
    Æ
    2.07
    T
    2.07
     indiquer
    2.06
     Inver
    2.06
    Activations Density 0.035%

    No Known Activations