© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62735
    Prev
    Next
    INDEX
    Explanations

    call for help

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

    The neuron fires on words that name the purpose or function given after “for” (e.g. lighting, signaling, decoration, help).

    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
     ZE
    -0.83
    Réponse
    -0.76
    ⓚ
    -0.74
     retourner
    -0.74
     krem
    -0.73
    Puissance
    -0.71
    Unnamed
    -0.71
     saad
    -0.71
     viser
    -0.70
    Membre
    -0.70
    POSITIVE LOGITS
     SOS
    4.56
    SOS
    3.91
     distress
    2.92
    sos
    2.80
     sos
    2.72
     Sos
    2.36
     emergency
    2.34
    Sos
    2.27
     Distress
    2.25
     HELP
    2.09
    Activations Density 0.036%

    No Known Activations