© 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. 128226
    Prev
    Next
    INDEX
    Explanations

    things that float

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

    The neuron fires on any form or derivative of the root “float,” e.g. “float,” “floats,” “floating,” or “floatables.”

    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
    9
    -2.38
    2
    -2.31
    3
    -2.25
    7
    -2.19
    4
    -2.16
    導致
    -2.16
     saranno
    -2.14
    6
    -2.11
    when
    -2.09
    5
    -2.09
    POSITIVE LOGITS
    ]
    2.94
    ;
    2.75
    }
    2.47
    ೢ
    2.42
     immeasurable
    2.20
    *
    2.17
    ꜄
    2.13
    ’
    2.08
     interconnected
    2.06
    ྂ
    2.06
    Activations Density 0.009%

    No Known Activations