© 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. 8147
    Prev
    Next
    INDEX
    Explanations

    quantify if possible

    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
    ARY
    1.73
    AK
    1.62
    APT
    1.60
    䋇
    1.60
    ের
    1.59
    ING
    1.57
    АР
    1.56
    䋆
    1.55
    ARE
    1.55
    THAT
    1.55
    POSITIVE LOGITS
    ista
    1.37
    idae
    1.26
    Nes
    1.17
    isty
    1.14
    istas
    1.09
     клад
    1.06
    co
    1.05
    istan
    1.05
     hùng
    1.04
    iste
    1.04
    Activations Density 0.040%

    No Known Activations