© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 11494
    Prev
    Next
    INDEX
    Explanations

    это, це, один, хороший

    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
    \]
    2.59
    ected
    2.54
    ार
    2.47
    alem
    2.45
    জনক
    2.32
    auri
    2.30
    াকা
    2.25
    𝐡
    2.21
    ível
    2.19
    aurants
    2.15
    POSITIVE LOGITS
    קס
    2.81
    PluginResult
    2.55
    ථා
    2.54
    plers
    2.53
    browserAction
    2.52
     மீது
    2.46
    딜
    2.41
    /−
    2.37
    icone
    2.36
    KeyboardMarkup
    2.34
    Activations Density 0.000%

    No Known Activations