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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 104869
    Prev
    Next
    INDEX
    Explanations

    code punctuation and identifiers

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

    the asterisk character used in pointer declarations in C/C++ 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
     their
    -1.63
    es
    -1.51
     there
    -1.49
     $
    -1.42
     about
    -1.37
     they
    -1.35
     If
    -1.32
     There
    -1.30
    vestres
    -1.27
    这也是
    -1.25
    POSITIVE LOGITS
     its
    1.48
     verificación
    1.40
     Preferencias
    1.38
    tième
    1.35
     zosta
    1.35
     commerciales
    1.35
     deň
    1.35
    asih
    1.34
     but
    1.33
     assolu
    1.32
    Activations Density 0.010%

    No Known Activations