© 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. 107872
    Prev
    Next
    INDEX
    Explanations

    posted by or by date

    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_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
     unequivocally
    -1.13
     when
    -1.09
     or
    -1.08
     utterly
    -1.07
     it
    -1.07
     four
    -1.04
     supposedly
    -1.04
     any
    -1.02
     really
    -1.01
     espagnol
    -1.00
    POSITIVE LOGITS
    <h4>
    1.16
    @[+][
    1.13
    などが
    1.12
     übrigen
    1.09
     NONE
    1.08
    echos
    1.06
     •
    1.05
    ingue
    1.05
     другие
    1.05
     undefined
    1.05
    Activations Density 0.054%

    No Known Activations