© 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. 7671
    Prev
    Next
    INDEX
    Explanations

    Erlang, OTP, module, pid, gen, akka

    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
     zina
    -1.35
     rute
    -1.21
     kuah
    -1.17
     territo
    -1.14
     alip
    -1.13
     osal
    -1.12
     AGAIN
    -1.09
    防災
    -1.09
     blah
    -1.09
     Igles
    -1.07
    POSITIVE LOGITS
    ></
    1.34
     outros
    1.27
    xit
    1.23
    justifyContent
    1.22
     Od
    1.22
     other
    1.22
    ictured
    1.18
    }+
    1.17
     kvalit
    1.16
    อื่น
    1.16
    Activations Density 0.072%

    No Known Activations