© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1672
    Prev
    Next
    INDEX
    Explanations

    lists of items and states

    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_65k_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
    é
    1.56
    ärm
    1.44
    és
    1.43
    خر
    1.43
     przec
    1.42
    ätt
    1.42
    decoded
    1.38
    oir
    1.36
     தோல்
    1.34
    openapi
    1.33
    POSITIVE LOGITS
    পুরের
    1.44
    𝘶
    1.41
     Bik
    1.38
    ϴ
    1.38
     Bors
    1.34
    ικής
    1.34
    在于
    1.33
    KET
    1.32
     ∣
    1.31
     △
    1.31
    Activations Density 0.000%

    No Known Activations