© 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. 10-GEMMASCOPE-RES-131K
    7. 44001
    Prev
    Next
    INDEX
    Explanations

    daily frequency or publication name

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

    This neuron detects frequency or interval keywords (like “daily” and “weekly”) often appearing alongside numeric values.

    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
    ↵
    -2.30
    ↵↵
    -2.09
     あります
    -1.90
    使う
    -1.88
    凄い
    -1.84
    ’
    -1.84
     Meksiko
    -1.84
    NOSIS
    -1.83
    нную
    -1.80
    >
    -1.78
    POSITIVE LOGITS
    )
    2.72
    this
    2.48
    This
    2.38
    When
    2.38
    ]
    2.19
     ему
    2.14
    just
    2.09
    From
    2.09
     when
    1.99
     because
    1.97
    Activations Density 0.014%

    No Known Activations