© 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. 128033
    Prev
    Next
    INDEX
    Explanations

    ahead of time or schedule

    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
    }
    -2.75
    u
    -2.70
     p
    -2.42
    -
    -2.42
    ”
    -2.38
    be
    -2.34
    "
    -2.28
     o
    -2.27
    1
    -2.23
     notorious
    -2.20
    POSITIVE LOGITS
     frança
    3.14
     aussit
    2.95
     inoxydable
    2.94
    ଝ
    2.83
     pauv
    2.80
     zoude
    2.66
     unie
    2.63
     skak
    2.59
    ientras
    2.58
     charmant
    2.58
    Activations Density 0.004%

    No Known Activations