© 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. 15102
    Prev
    Next
    INDEX
    Explanations

    greeting or question followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     gmina
    -1.16
     INGRED
    -1.11
    roskop
    -1.08
     hini
    -1.05
    cepcion
    -1.05
    Véxase
    -1.04
     magnitud
    -1.03
    لیس
    -1.02
     tami
    -1.01
    roën
    -1.00
    POSITIVE LOGITS
     amd
    1.18
     they
    1.16
     admiten
    1.06
    様です
    1.05
    短短
    1.00
     stalwart
    1.00
     Exteriores
    0.98
     insane
    0.98
     tratan
    0.97
     zuerst
    0.96
    Activations Density 0.000%

    No Known Activations