© 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. 15010
    Prev
    Next
    INDEX
    Explanations

    conditional statements with when

    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
    пита
    1.69
    𝙏
    1.68
     راح
    1.65
     دى
    1.59
    ެވެ
    1.56
     sails
    1.56
    აკ
    1.53
    ampo
    1.51
    ﺒ
    1.50
    टना
    1.49
    POSITIVE LOGITS
     και
    2.01
    触摸
    2.00
    νό
    1.96
     concentração
    1.95
    stones
    1.90
    γι
    1.90
     patham
    1.84
     στον
    1.80
     faudrait
    1.78
     concentración
    1.78
    Activations Density 0.000%

    No Known Activations