© 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. 22-GEMMASCOPE-RES-131K
    7. 66355
    Prev
    Next
    INDEX
    Explanations

    numbers and Q

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

    The neuron flags numeric tokens that include decimal points (i.e. fractional population or measurement figures).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     我
    -1.13
     hacían
    -1.12
    CloseHandle
    -1.07
    ］
    -1.05
    katakan
    -1.05
    ():
    -1.04
    lecteur
    -1.02
    ]=>
    -1.02
    logies
    -1.01
    antwoorde
    -1.01
    POSITIVE LOGITS
     delicioso
    1.34
     fewer
    1.28
     разные
    1.14
     feu
    1.13
    Funktionen
    1.11
     verschiedene
    1.10
    Haben
    1.10
    Matéri
    1.09
     entangled
    1.08
    かわらず
    1.08
    Activations Density 0.002%

    No Known Activations