© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10365
    Prev
    Next
    INDEX
    Explanations

    counting distinct items

    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
    Negative Logits
    뻗
    2.58
    ීම
    2.56
    멋
    2.56
    껄
    2.53
    끝
    2.51
    doctype
    2.47
    کھ
    2.37
    鸞
    2.37
    ̉a
    2.36
    动手
    2.36
    POSITIVE LOGITS
    enance
    2.82
    えます
    2.60
    えない
    2.55
    नाइटेड
    2.51
    える
    2.50
    えて
    2.44
    enaire
    2.44
     Bata
    2.41
    ውነ
    2.40
    ॅमिली
    2.40
    Activations Density 0.013%

    No Known Activations