© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 102489
    Prev
    Next
    INDEX
    Explanations

    indefinite pronouns and elsewhere

    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_34/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
     endereço
    -0.93
     wszystkie
    -0.92
    }=\
    -0.88
    如有
    -0.86
     algunos
    -0.86
     наших
    -0.85
    alay
    -0.85
    HXLINE
    -0.83
     neby
    -0.82
    <0xD9>
    -0.82
    POSITIVE LOGITS
     else
    8.31
    else
    5.75
     Else
    4.03
     ELSE
    3.98
    Else
    3.86
    ELSE
    3.69
    อื่น
    3.63
     other
    3.28
     elsewhere
    2.84
     others
    2.67
    Activations Density 0.053%

    No Known Activations