© 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. 15304
    Prev
    Next
    INDEX
    Explanations

    C followed by Tag, | followed by false, Sig followed by vard

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

    This neuron responds to multi-digit numbers (numeric tokens with two or more digits).

    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
     will
    -1.15
     of
    -1.13
    Olvid
    -1.02
    ஶ
    -1.02
    hombre
    -1.01
    jint
    -0.93
    haling
    -0.91
     metálica
    -0.91
    TestBed
    -0.90
    訖
    -0.90
    POSITIVE LOGITS
     pezzo
    1.02
     gesuchten
    1.01
    ──
    1.01
    },
    0.99
    螂
    0.99
     へ
    0.96
     reduziert
    0.92
    oczes
    0.91
     salles
    0.91
     './../
    0.91
    Activations Density 0.001%

    No Known Activations