© 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. 22-GEMMASCOPE-RES-131K
    7. 25533
    Prev
    Next
    INDEX
    Explanations

    UI elements and code snippets

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

    The neuron activates whenever it sees the word “Input” (as in a layer or function call defining an input tensor).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    を
    -1.58
    が上が
    -1.52
    などを
    -1.46
    などの
    -1.38
    与此同时
    -1.37
    に関して
    -1.34
    vereign
    -1.31
    も多く
    -1.31
    それにしても
    -1.30
    1
    -1.30
    POSITIVE LOGITS
    んですよ
    1.55
     hombro
    1.40
    ようですが
    1.38
     profundos
    1.38
     rápidos
    1.38
     you
    1.38
     decorativos
    1.36
     cinturón
    1.34
    気がします
    1.33
     zatem
    1.33
    Activations Density 0.000%

    No Known Activations