© 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. 22-GEMMASCOPE-RES-131K
    7. 26853
    Prev
    Next
    INDEX
    Explanations

    book followed by noun

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

    The neuron is highly activated by occurrences of “book” (in any casing or plural form).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    
    -2.59
    缭
    -2.41
    咴
    -2.28
    拶
    -2.27
     richting
    -2.22
    ឵
    -2.19
    イクアウト
    -2.16
     Trouver
    -2.05
     --
    -2.03
     incomparable
    -2.03
    POSITIVE LOGITS
    ديو
    2.64
    indelijk
    2.61
    ため
    2.61
    」
    2.44
    From
    2.44
    ۶
    2.39
    Recently
    2.39
    with
    2.36
    With
    2.28
    Currently
    2.27
    Activations Density 0.032%

    No Known Activations