© 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. 185056
    Prev
    Next
    INDEX
    Explanations

    your statement

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

    how language is used

    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
    ходил
    0.41
    краё
    0.41
    rocery
    0.40
     jednego
    0.39
    ElapsedTime
    0.39
    味わ
    0.39
    ोरेशन
    0.39
    సాగ
    0.39
    滲
    0.39
     houve
    0.38
    POSITIVE LOGITS
    ²
    0.47
     letto
    0.45
     neoplastic
    0.45
     SCSI
    0.44
     consonant
    0.44
    C
    0.44
    and
    0.44
     unsurprisingly
    0.43
    ၼ်
    0.43
     Toshiba
    0.43
    Activations Density 0.000%

    No Known Activations