© 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. 11744
    Prev
    Next
    INDEX
    Explanations

    Apache and SAFE

    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
    atile
    2.62
    ˩
    2.48
     estrella
    2.44
     plen
    2.41
    öö
    2.40
    ု
    2.35
     माला
    2.34
    述
    2.32
    います
    2.32
     बिता
    2.32
    POSITIVE LOGITS
    DEFGHIJKLMNOP
    2.51
    bbero
    2.45
    ்க
    2.42
    брать
    2.39
    sink
    2.32
    nonumber
    2.31
    ிறது
    2.31
    InitStruct
    2.30
    ரம்
    2.26
    ोले
    2.21
    Activations Density 0.043%

    No Known Activations