© 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. 49282
    Prev
    Next
    INDEX
    Explanations

    adjectival or adverb

    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
    aita
    -0.76
    lň
    -0.70
     Wechsel
    -0.69
     обна
    -0.66
    òng
    -0.66
    ctron
    -0.65
     Reasonable
    -0.65
     Aha
    -0.64
    donor
    -0.64
    ån
    -0.64
    POSITIVE LOGITS
     adjective
    4.13
     adjectives
    3.63
    adjective
    3.00
     adj
    2.89
    adj
    2.56
    形容
    2.44
     Adj
    2.31
    Ad
    2.30
     Ad
    2.27
    Adj
    2.25
    Activations Density 0.052%

    No Known Activations