© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 13034
    Prev
    Next
    INDEX
    Explanations

    volunteer and volunteering

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

    volunteer activities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    0.57
     pounding
    0.52
    ви
    0.50
    在
    0.50
     तापमान
    0.49
    h
    0.49
     液
    0.47
    ।’’
    0.46
     증
    0.46
     হাম
    0.46
    POSITIVE LOGITS
     volunteer
    1.02
     volunteers
    0.99
    volunteer
    0.99
     Volunteer
    0.98
    Volunteer
    0.96
     Volunteers
    0.90
     volunt
    0.90
     volont
    0.88
     volunteering
    0.85
     Volunte
    0.84
    Activations Density 0.054%

    No Known Activations