© 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. 35102
    Prev
    Next
    INDEX
    Explanations

    Starts of specific phrases

    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
    '],
    -1.48
    ävät
    -1.24
     requer
    -1.23
     with
    -1.19
    MatInputModule
    -1.16
     it
    -1.13
     without
    -1.11
    rightarrow
    -1.11
    equalTo
    -1.10
     tardes
    -1.09
    POSITIVE LOGITS
     récents
    1.39
    そも
    1.35
     applau
    1.28
    WAITING
    1.28
    腟
    1.27
     diverses
    1.27
    膣
    1.26
     ſever
    1.24
     réguli
    1.23
     magnifiques
    1.23
    Activations Density 0.002%

    No Known Activations