© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91375
    Prev
    Next
    INDEX
    Explanations

    sign up or sign in

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

    The neuron strongly activates on “Sign” plus a following “Up” or “In,” i.e. on calls‐to‐action prompting the user to sign up or log in.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    iline
    -0.79
     זאת
    -0.68
    Brin
    -0.68
    assoc
    -0.67
    ظهار
    -0.66
    郑州
    -0.66
     Ches
    -0.66
     it
    -0.65
     expected
    -0.65
    報告
    -0.64
    POSITIVE LOGITS
     up
    2.11
     signed
    1.23
    up
    1.17
    Up
    1.16
     signings
    1.12
     signing
    1.10
     signer
    1.09
     Up
    1.04
    Unsigned
    0.98
     Signing
    0.97
    Activations Density 0.014%

    No Known Activations