© 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. 34-GEMMASCOPE-RES-131K
    7. 91778
    Prev
    Next
    INDEX
    Explanations

    release dates

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

    The neuron flags date expressions—especially month names and their accompanying day‐and‐year numerals.

    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
     after
    -1.15
     started
    -0.85
     would
    -0.84
     evening
    -0.84
     during
    -0.82
     at
    -0.80
     when
    -0.80
     serious
    -0.79
     hubo
    -0.79
     based
    -0.76
    POSITIVE LOGITS
     release
    1.66
    release
    1.55
     released
    1.53
     releases
    1.52
    Release
    1.45
    Releases
    1.42
    RELEASE
    1.38
    releases
    1.36
    released
    1.35
     Release
    1.29
    Activations Density 0.049%

    No Known Activations