© 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. 57724
    Prev
    Next
    INDEX
    Explanations

    academic references

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

    The neuron flags in-text citation markers and bibliography reference tokens (e.g. “ref” labels and similar reference identifiers).

    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
     zade
    -0.80
    SPO
    -0.79
    RESS
    -0.75
     Firmen
    -0.73
     edades
    -0.71
     переза
    -0.71
    店的
    -0.71
     colabor
    -0.69
    アンサー
    -0.69
     ofer
    -0.68
    POSITIVE LOGITS
     đậu
    0.75
    옹
    0.71
    Crystal
    0.71
     multilayer
    0.69
    Signal
    0.68
     پر
    0.68
    亲
    0.68
    elis
    0.68
    個
    0.67
    TintColor
    0.66
    Activations Density 0.027%

    No Known Activations