© 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. 34-GEMMASCOPE-RES-131K
    7. 1918
    Prev
    Next
    INDEX
    Explanations

    bass prefix

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

    This neuron activates on the substring “bass,” picking up both the word “bass” (as in instruments) and names beginning with “Bass.”

    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
    er
    -0.77
    estia
    -0.74
    强制
    -0.72
     clamps
    -0.72
    MHC
    -0.71
     juez
    -0.71
    охра
    -0.70
    tot
    -0.69
    十分的
    -0.69
    ia
    -0.69
    POSITIVE LOGITS
    oon
    1.01
    getB
    0.82
     FISHING
    0.77
    ungere
    0.76
     ↓,
    0.73
     尼
    0.72
    étr
    0.71
    امین
    0.71
     Regierungs
    0.71
    czerw
    0.71
    Activations Density 0.016%

    No Known Activations