© 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. 22-GEMMASCOPE-RES-131K
    7. 127958
    Prev
    Next
    INDEX
    Explanations

    regarding pointers

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    especial
    -1.19
    hmmmm
    -1.12
    UNIDAD
    -1.12
     konsult
    -1.08
    агностика
    -1.08
    honestly
    -1.08
    calculated
    -1.07
    saison
    -1.06
    bew
    -1.05
    stainless
    -1.05
    POSITIVE LOGITS
     данного
    1.42
     since
    1.26
     given
    1.23
     although
    1.21
     because
    1.20
     refers
    1.13
     only
    1.12
     бампер
    1.12
     данном
    1.09
     whereas
    1.07
    Activations Density 0.009%

    No Known Activations