© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65056
    Prev
    Next
    INDEX
    Explanations

    words starting with out

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

    The neuron activates strongly on words beginning with the prefix “out.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     помогает
    -1.03
     selben
    -1.03
    }$
    -1.02
    快要
    -1.02
    );
    -1.02
    </i>
    -0.99
    コト
    -0.99
     outlook
    -0.96
    rdı
    -0.94
    jährigen
    -0.94
    POSITIVE LOGITS
    
    1.12
    ting
    1.10
     bleu
    1.08
    dent
    1.07
     για
    1.05
    laws
    1.04
     DISEASE
    1.02
     να
    1.01
    mands
    1.00
    ंस
    1.00
    Activations Density 0.021%

    No Known Activations