© 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. 22-GEMMASCOPE-RES-131K
    7. 65019
    Prev
    Next
    INDEX
    Explanations

    happy birthday and similar

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    '
    -2.66
     dando
    -2.56
     '
    -2.56
     republiky
    -2.50
     diversos
    -2.44
    𐀀
    -2.38
     suporta
    -2.36
    菝
    -2.31
    </strong>
    -2.31
     crear
    -2.30
    POSITIVE LOGITS
    Also
    3.45
    0
    3.28
    7
    3.27
    Despite
    3.11
    Unlike
    3.05
    Although
    3.02
    4
    2.97
    8
    2.92
    Following
    2.89
    Probably
    2.88
    Activations Density 0.008%

    No Known Activations