© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34996
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    μένων
    -1.27
    cestors
    -1.18
     kebaikan
    -1.13
     their
    -1.10
    MENTE
    -1.10
    　『
    -1.09
     persil
    -1.08
    🦋
    -1.06
     voyez
    -1.05
    dekat
    -1.05
    POSITIVE LOGITS
    u
    1.19
    ur
    1.07
    ce
    1.05
    ze
    1.04
     C
    1.02
     U
    1.01
    wa
    1.01
     wenigstens
    1.00
     provavelmente
    1.00
    min
    0.99
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.