© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15824
    Prev
    Next
    INDEX
    Explanations

    guerilla or question prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    0
    -3.30
    2
    -2.61
    ce
    -2.55
    z
    -2.30
    ven
    -2.20
    ha
    -2.17
    f
    -2.16
    pa
    -2.14
     for
    -2.11
    ными
    -2.11
    POSITIVE LOGITS
    the
    2.64
     óptica
    2.59
     demasi
    2.53
     queridos
    2.44
     bezit
    2.36
     voordeel
    2.28
     poderosos
    2.27
     gewinnt
    2.19
     moest
    2.16
    巂
    2.16
    Activations Density 0.000%

    No Known Activations