© 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. 226612
    Prev
    Next
    INDEX
    Explanations

    card only

    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
     собственные
    0.49
    iens
    0.47
     Defensa
    0.47
    Own
    0.45
     বাঙালিদের
    0.45
     PIB
    0.45
     സ്വന്ത
    0.45
    뜩
    0.44
    ሉ።
    0.44
    ieme
    0.43
    POSITIVE LOGITS
    adjustable
    0.49
    rad
    0.45
     và
    0.44
    fork
    0.43
    marking
    0.43
     follicular
    0.43
    ᴏ
    0.42
     reaffirm
    0.42
    ꜰ
    0.42
    ciphertext
    0.41
    Activations Density 0.000%

    No Known Activations