© 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. 13-GEMMASCOPE-2-RES-16K
    7. 14877
    Prev
    Next
    INDEX
    Explanations

    pip install commands

    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_13_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
    <unused1461>
    2.30
    𒁍
    2.28
    𒁁
    2.27
    slideDuplicate
    2.25
    𒉋
    2.24
    𒂆
    2.22
    𒌇
    2.21
    atthane
    2.21
    𒂅
    2.21
    <unused57>
    2.21
    POSITIVE LOGITS
    es
    1.23
    1
    1.10
    2
    1.07
     (
    1.06
    (
    1.05
     of
    1.03
     this
    1.00
     not
    0.98
    ’
    0.98
    This
    0.97
    Activations Density 0.001%

    No Known Activations