© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 131489
    Prev
    Next
    INDEX
    Explanations

    facilities, assurance, people, removing, buttons

    np_acts-logits-general · gemini-2.5-flash-lite

    share contextually relevant information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h2>
    0.49
     attenuation
    0.47
     LIMIT
    0.44
     limit
    0.44
     grate
    0.44
    ಾಪ
    0.43
     maximum
    0.42
    ITURE
    0.41
     clove
    0.41
    Zm
    0.40
    POSITIVE LOGITS
    veratrol
    0.47
    骈
    0.46
     convincingly
    0.46
    ategor
    0.46
    relevant
    0.45
    शिक्ष
    0.45
    骯
    0.45
     égal
    0.44
     intéress
    0.44
     analiz
    0.44
    Activations Density 0.001%

    No Known Activations