© 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. 34-GEMMASCOPE-RES-131K
    4. 110961
    Prev
    Next
    INDEX
    Explanations

    simplify, collect, what

    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
    soort
    -1.00
    opheles
    -0.94
    ம்ப
    -0.94
    esthes
    -0.94
     davvero
    -0.92
     féminin
    -0.89
     inesperado
    -0.89
     contraire
    -0.87
     edil
    -0.86
    vaného
    -0.86
    POSITIVE LOGITS
    bsen
    0.99
    ‌ی
    0.96
    })$,
    0.96
    ियों
    0.96
    }}-\
    0.94
    }}{\
    0.94
    IN
    0.93
    into
    0.92
    )}=\
    0.91
     coloca
    0.90
    Activations Density 0.005%

    No Known Activations