© 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. 12708
    Prev
    Next
    INDEX
    Explanations

    ‘bout a, ‘cause

    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
     het
    1.63
     By
    1.58
    1.54
    in
    1.53
     As
    1.50
     L
    1.49
     A
    1.46
     ‘
    1.41
     And
    1.41
     d
    1.40
    POSITIVE LOGITS
    pcid
    2.19
    Чи
    2.18
    াপা
    2.06
    ifaiFace
    2.04
    ጣት
    2.04
     теркәлүсез
    2.02
    <unused900>
    2.01
    cimiento
    2.01
    Ти
    2.00
     Fairchild
    2.00
    Activations Density 0.007%

    No Known Activations