© 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. 129142
    Prev
    Next
    INDEX
    Explanations

    intensifiers

    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
    が
    -1.21
    を
    -1.16
    Nyc
    -1.14
    vák
    -1.10
    などを
    -1.05
    <bos>
    -1.02
     لأنه
    -1.01
    も
    -1.00
    
    -0.98
    子が
    -0.98
    POSITIVE LOGITS
    ところに
    1.25
    様な
    1.17
     pueden
    1.14
     profundas
    1.08
    に行って
    1.07
    為に
    1.07
     Vereinigten
    1.06
    すっ
    1.05
     murió
    1.05
    把自己
    1.05
    Activations Density 0.064%

    No Known Activations