© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77813
    Prev
    Next
    INDEX
    Explanations

    book reviews and readability

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

    The neuron fires on positive evaluative language (praises and upbeat descriptive adjectives or adverbs).

    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
    }}},
    -0.92
     Zuschauer
    -0.90
    を見て
    -0.86
    ünstig
    -0.85
    EOUS
    -0.82
    ถม
    -0.80
    ρης
    -0.78
     toată
    -0.76
    ᴾ
    -0.75
    arities
    -0.75
    POSITIVE LOGITS
     readability
    1.78
     reads
    1.76
     readable
    1.69
     read
    1.63
     entertaining
    1.53
     enjoyable
    1.51
     fast
    1.45
    readable
    1.41
    Reads
    1.38
     entertainment
    1.34
    Activations Density 0.025%

    No Known Activations