© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 179015
    Prev
    Next
    INDEX
    Explanations

    end of phrase leading to next

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

    understanding your

    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
    Not in Any Lists

    No Comments

    Negative Logits
    .
    0.45
    IZER
    0.44
     ON
    0.43
     nears
    0.43
     generalizes
    0.43
     ACS
    0.42
     exteriores
    0.42
    MAD
    0.41
     disables
    0.41
     হইয়৷
    0.41
    POSITIVE LOGITS
    äche
    0.54
    pèce
    0.53
     सिंहासन
    0.51
     취
    0.50
     आकार
    0.50
     तकलीफ
    0.49
    itabbam
    0.48
     Tudo
    0.47
    attitude
    0.47
     ज्ञा
    0.47
    Activations Density 0.000%

    No Known Activations