© 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. 12608
    Prev
    Next
    INDEX
    Explanations

    all followed by linking words

    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
     directional
    2.04
    iguity
    2.04
    heer
    2.04
    virk
    2.03
    ة
    2.02
    ﻞ
    1.98
    itz
    1.92
     feature
    1.89
    ight
    1.85
    ebab
    1.81
    POSITIVE LOGITS
    dehyde
    2.81
    wsgi
    2.49
    setupUi
    2.49
     இதனால்
    2.46
    étale
    2.38
    🅻
    2.35
    шем
    2.35
    Título
    2.33
    వ్వు
    2.28
    ñoz
    2.25
    Activations Density 0.142%

    No Known Activations