© 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. 3841
    Prev
    Next
    INDEX
    Explanations

    more or less descriptions

    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
    ISSION
    2.25
    ყოფ
    2.20
    屼
    2.19
    <unused2004>
    2.10
    屽
    2.09
    岄
    2.08
    ANS
    2.08
    ्हे
    2.02
    quan
    2.00
     Dokl
    1.98
    POSITIVE LOGITS
     lemb
    2.00
     마을
    1.98
     agak
    1.94
     de
    1.77
     சற்று
    1.76
     சிறிது
    1.75
     민
    1.74
     settle
    1.72
     fuga
    1.70
     겸
    1.70
    Activations Density 0.171%

    No Known Activations