© 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. 13-GEMMASCOPE-2-RES-16K
    7. 6856
    Prev
    Next
    INDEX
    Explanations

    incrementing or decrementing code

    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
    ypes
    1.40
     optic
    1.31
     delicate
    1.28
    etel
    1.27
    睚
    1.26
    clesiastical
    1.24
    Worldwide
    1.24
    cherichia
    1.24
    वड
    1.23
     volatile
    1.22
    POSITIVE LOGITS
     <!--<
    1.32
     חו
    1.29
     profesora
    1.24
     $=
    1.23
     thầy
    1.23
     पवार
    1.22
     Aap
    1.21
    Pad
    1.21
     recomm
    1.19
     Ran
    1.19
    Activations Density 0.010%

    No Known Activations