© 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. 43689
    Prev
    Next
    INDEX
    Explanations

    guaranteed

    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_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
     quando
    -2.63
    ൮
    -2.52
     pero
    -2.39
    ࿊
    -2.38
    URLConnection
    -2.36
    ндарт
    -2.31
    ܆
    -2.30
    ╽
    -2.30
    ſſi
    -2.28
    ޏ
    -2.27
    POSITIVE LOGITS
    '
    3.05
    s
    3.05
    While
    2.86
    With
    2.84
    What
    2.84
    Because
    2.78
    Although
    2.64
    This
    2.63
    There
    2.58
    Surprisingly
    2.58
    Activations Density 0.002%

    No Known Activations