© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76332
    Prev
    Next
    INDEX
    Explanations

    names with 'ott'/'ett' endings

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

    The neuron selectively activates on tokens containing a double “tt” sequence (e.g. in surnames).

    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
    ）」
    -0.79
    inės
    -0.75
    aye
    -0.74
    度に
    -0.73
    HOUT
    -0.73
    buri
    -0.73
     Mandarin
    -0.72
    収納
    -0.72
     spanish
    -0.70
    dac
    -0.69
    POSITIVE LOGITS
    GetLength
    0.79
    issipp
    0.73
    Autoritní
    0.73
    が発
    0.71
    necessary
    0.71
     misschien
    0.71
     precies
    0.71
    sistency
    0.71
    gens
    0.68
     Required
    0.68
    Activations Density 0.036%

    No Known Activations