© 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. 10-GEMMASCOPE-RES-131K
    7. 7820
    Prev
    Next
    INDEX
    Explanations

    go the distance

    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_10/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
    when
    -2.17
    Getting
    -2.14
    Surprisingly
    -2.11
     RSITY
    -2.11
    Following
    -2.09
     laajenta
    -2.09
     julk
    -2.02
    鱘
    -2.00
    Having
    -2.00
     that
    -2.00
    POSITIVE LOGITS
    ↵
    2.53
     Our
    2.45
     myriad
    2.44
    .
    2.30
     —
    2.25
    ,”
    2.16
     kinda
    2.14
     mediocre
    2.14
     momentous
    2.13
    ⬈
    2.11
    Activations Density 0.010%

    No Known Activations