© 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. 127682
    Prev
    Next
    INDEX
    Explanations

    form of the other

    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
    Negative Logits
     אינו
    -1.09
    Despite
    -1.08
    Since
    -1.02
     lecz
    -1.02
    Though
    -1.02
    áját
    -1.00
    Ἡ
    -0.98
     Though
    -0.98
     despite
    -0.98
     boasts
    -0.97
    POSITIVE LOGITS
     somebody
    1.77
     you
    1.58
     everybody
    1.55
    inaudible
    1.52
     really
    1.44
     wonderful
    1.44
    really
    1.39
     kind
    1.37
    everybody
    1.34
     things
    1.29
    Activations Density 0.118%

    No Known Activations