© 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
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5505
    Prev
    Next
    INDEX
    Explanations

    namely, in other words, that is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    0.66
    ;
    0.66
    '/>
    0.65
    ?...
    0.64
    But
    0.63
     them
    0.63
    ...";
    0.62
     新作
    0.61
    뀔
    0.61
    ;%(
    0.60
    POSITIVE LOGITS
     i
    2.48
     yani
    1.64
    i
    1.62
     یعنی
    1.62
    つまり
    1.58
     cioè
    1.55
     यानी
    1.52
     тобто
    1.51
     অর্থাৎ
    1.49
     namely
    1.49
    Activations Density 0.139%

    No Known Activations