© 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. 11441
    Prev
    Next
    INDEX
    Explanations

    python -m

    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
    رر
    1.65
    েবের
    1.53
    ម្ម
    1.51
    ocsát
    1.50
    觟
    1.50
    แนน
    1.48
    らを
    1.47
    iemi
    1.44
    روس
    1.44
    sie
    1.43
    POSITIVE LOGITS
    Ħ
    1.16
    al
    1.16
    QtCore
    1.13
    ️
    1.11
     '$
    1.11
    ḥ
    1.10
    an
    1.09
    Լ
    1.09
    Buff
    1.08
    $
    1.06
    Activations Density 0.008%

    No Known Activations