© 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. 72118
    Prev
    Next
    INDEX
    Explanations

    instead without

    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
    item
    -0.85
    +#+#
    -0.85
    将其
    -0.82
    jeeling
    -0.78
    Pause
    -0.77
    atsch
    -0.77
    Prop
    -0.76
     item
    -0.76
    Make
    -0.74
     objek
    -0.74
    POSITIVE LOGITS
     without
    1.51
     instead
    1.32
    celess
    1.20
     tanpa
    1.18
     χωρίς
    1.13
     Instead
    1.10
    Instead
    1.06
    不需要
    1.05
     вместо
    1.03
    不用
    1.00
    Activations Density 0.208%

    No Known Activations