© 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. 7-GEMMASCOPE-2-RES-16K
    7. 13464
    Prev
    Next
    INDEX
    Explanations

    по-русски

    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
    ే
    3.38
    n
    3.08
    niv
    2.88
    nage
    2.86
    ের
    2.82
    imc
    2.75
    keiten
    2.73
    nity
    2.69
    s
    2.67
    nosti
    2.67
    POSITIVE LOGITS
    JsonProperty
    3.27
    FromJson
    2.68
    SETTINGS
    2.62
    рого
    2.60
    Coca
    2.49
    ঃখ
    2.42
    Diethyl
    2.42
    Constitution
    2.39
    𝙿
    2.37
    𝙋
    2.36
    Activations Density 0.000%

    No Known Activations