© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 128373
    Prev
    Next
    INDEX
    Explanations

    acts as an aid

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

    The neuron activates on the verb “helps” (including its uses like “helps you…” or “helps to…”).

    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
    餮
    -2.78
    皞
    -2.27
    玏
    -2.25
    𔘓
    -2.22
     gier
    -2.14
    towy
    -2.14
    푏
    -2.14
     determinar
    -2.13
    ꔛ
    -2.11
    cheduler
    -2.09
    POSITIVE LOGITS
     However
    2.92
     While
    2.78
     Each
    2.59
     Which
    2.50
     Unfortunately
    2.36
     There
    2.33
     =
    2.30
     Doesn
    2.30
     Both
    2.28
     Does
    2.25
    Activations Density 0.007%

    No Known Activations