© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 102752
    Prev
    Next
    INDEX
    Explanations

    code identifiers after punctuation

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

    the period character following object property access in JavaScript code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    Not in Any Lists

    No Comments

    Negative Logits
    0
    -2.02
     also
    -1.87
     had
    -1.86
     can
    -1.79
     may
    -1.55
     became
    -1.48
     gives
    -1.43
     speziellen
    -1.41
     were
    -1.38
     represents
    -1.38
    POSITIVE LOGITS
    
    1.67
    %;
    1.59
    都不会
    1.52
     WORKSHOP
    1.51
    casino
    1.47
    祤
    1.45
    enablog
    1.45
    arted
    1.45
     following
    1.45
    杁
    1.44
    Activations Density 0.002%

    No Known Activations