© 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. 14090
    Prev
    Next
    INDEX
    Explanations

    advanced stages, fast speed, efficient

    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
    cím
    -1.24
     graisse
    -1.20
     угло
    -1.16
    ʬ
    -1.16
     '-':
    -1.09
    FUENTES
    -1.09
    €“
    -1.08
     "..\..\
    -1.07
     لأ
    -1.06
    🏟
    -1.06
    POSITIVE LOGITS
    𝑍
    1.18
     laikā
    1.13
     Dapat
    1.08
     such
    1.07
    𝑗
    1.05
     após
    1.05
    ，
    1.04
    𝑈
    1.04
    醯
    1.04
     Anche
    1.02
    Activations Density 0.139%

    No Known Activations