© 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. 10-GEMMASCOPE-RES-131K
    7. 40586
    Prev
    Next
    INDEX
    Explanations

    sequences ending in 'v'

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

    This neuron detects short all-caps abbreviations or acronyms (e.g. “LV,” “OVD,” “v.”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    3
    -2.97
    “
    -2.95
    1
    -2.94
    selben
    -2.86
    }
    -2.67
    D
    -2.66
    P
    -2.56
    ]
    -2.50
    er
    -2.28
    at
    -2.23
    POSITIVE LOGITS
     "
    2.84
    ᡴ
    2.61
     estrictamente
    2.55
    ᚔ
    2.52
     "'
    2.52
    ！"
    2.41
     muchísimo
    2.36
    ungkinkan
    2.36
    。"
    2.34
    and
    2.33
    Activations Density 0.868%

    No Known Activations