© 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. 71101
    Prev
    Next
    INDEX
    Explanations

    repeated common words

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

    The neuron detects instances where the same word appears twice in a row (consecutive token repetition).

    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
    様な
    -1.20
    ⓒ
    -1.20
    }*/
    -1.19
     élimin
    -1.18
    渽
    -1.16
    Beskrivelse
    -1.16
     Lettres
    -1.11
    場合には
    -1.11
    >
    -1.10
    Deskripsi
    -1.10
    POSITIVE LOGITS
     to
    1.23
     of
    1.11
     inapropiados
    1.10
     by
    1.04
     recevrez
    1.03
     a
    1.02
     Kennt
    1.02
    才行
    0.98
     other
    0.98
     Landwirtschaft
    0.97
    Activations Density 0.021%

    No Known Activations