© 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. 142549
    Prev
    Next
    INDEX
    Explanations

    guest designer

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

    breakdown of costs

    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
     can
    0.48
     qui
    0.48
     plenty
    0.47
     a
    0.46
     Hered
    0.45
     are
    0.45
     trainable
    0.45
     derives
    0.44
     Gink
    0.44
     use
    0.44
    POSITIVE LOGITS
    Foto
    0.53
     धरना
    0.49
    波动
    0.48
    Má
    0.48
    Cantidad
    0.47
     특집
    0.46
    마
    0.46
    లుగా
    0.46
    轫
    0.46
     비밀
    0.46
    Activations Density 0.000%

    No Known Activations