© 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. 3323
    Prev
    Next
    INDEX
    Explanations

    nucleation, nucleus, acute, recursion

    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
    cstr
    1.31
     výro
    1.20
     सीतार
    1.16
    보
    1.14
    alic
    1.11
    胱
    1.11
     mdl
    1.11
    률
    1.10
    serializing
    1.10
     psal
    1.09
    POSITIVE LOGITS
    .$$
    1.28
     Opposite
    1.13
    ación
    1.07
    aredo
    1.04
    plete
    1.01
    és
    1.00
     portada
    0.99
     स्थान
    0.99
     aquela
    0.97
     fresher
    0.97
    Activations Density 0.065%

    No Known Activations