© 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. 129171
    Prev
    Next
    INDEX
    Explanations

    It was

    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
     can
    -1.52
     kram
    -1.19
    бус
    -1.12
    ようと
    -1.12
     manifesta
    -1.12
     karbon
    -1.10
     simpto
    -1.10
    StreamWriter
    -1.09
     are
    -1.08
     vekt
    -1.08
    POSITIVE LOGITS
     was
    1.89
     была
    1.24
     было
    1.24
    igth
    1.22
     был
    1.14
     étages
    1.13
    ggy
    1.07
     Отечественной
    1.07
     zwing
    1.06
    mbal
    1.05
    Activations Density 0.025%

    No Known Activations