© 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. 40819
    Prev
    Next
    INDEX
    Explanations

    signs of

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

    This neuron detects words that introduce indicators or warning cues—terms like “signs,” “clues,” “signals,” etc.

    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
    Identifying
    -1.41
    ி
    -1.39
    ０
    -1.36
    NOK
    -1.33
    nachweise
    -1.33
     condicionado
    -1.30
     saveur
    -1.29
    凛
    -1.28
     seule
    -1.27
     wesentlich
    -1.27
    POSITIVE LOGITS
     signs
    2.30
     that
    2.05
     Signs
    1.67
    man
    1.66
     This
    1.62
     verbess
    1.55
     zanahoria
    1.47
     passaram
    1.45
     SIGNS
    1.44
    ers
    1.41
    Activations Density 0.040%

    No Known Activations