© 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. 72321
    Prev
    Next
    INDEX
    Explanations

    member access in code

    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
    卝
    -1.22
     
    -1.22
    ཾ
    -1.21
    maining
    -1.20
    arrived
    -1.20
    gled
    -1.19
    ebly
    -1.17
    arrive
    -1.13
    greja
    -1.12
    entered
    -1.12
    POSITIVE LOGITS
     had
    1.17
     time
    1.14
     -
    1.13
     only
    1.11
     is
    1.11
     immensely
    1.09
     as
    1.08
     on
    1.08
     for
    1.08
     IN
    1.07
    Activations Density 0.001%

    No Known Activations