© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 163004
    Prev
    Next
    INDEX
    Explanations

    POS system, constitutes unauthorized, defines how

    np_acts-logits-general · gemini-2.5-flash-lite

    gentoo penguins or clustering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    E
    0.51
    DD
    0.47
    CEO
    0.46
    ني
    0.46
    L
    0.45
    D
    0.45
    3
    0.45
    DNA
    0.44
    TO
    0.44
    2
    0.44
    POSITIVE LOGITS
     ግራም
    0.48
     இடத்தில்
    0.46
     በጣም
    0.44
     cies
    0.43
     localities
    0.43
     நிலையம்
    0.43
     κάν
    0.43
     Мак
    0.43
     méthodes
    0.43
     агре
    0.43
    Activations Density 0.000%

    No Known Activations