© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 173956
    Prev
    Next
    INDEX
    Explanations

    come back

    np_acts-logits-general · gemini-2.5-flash-lite

    conditional statements or hypothetical situations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     இருப்பதால்
    0.42
     ಅಥವಾ
    0.42
     Тому
    0.42
     இப்ப
    0.41
    成为
    0.40
    𝘤
    0.40
     물질
    0.39
     रिलेशनशिप
    0.39
     BRIEF
    0.38
     Григо
    0.38
    POSITIVE LOGITS
     retort
    0.49
     broke
    0.48
     indulge
    0.46
    ))*
    0.46
     المنت
    0.45
     ><
    0.45
     defending
    0.45
     defended
    0.45
     refuses
    0.45
    Tried
    0.44
    Activations Density 0.000%

    No Known Activations