© 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. 206293
    Prev
    Next
    INDEX
    Explanations

    live webcast, dentist demonstrate, should concentrate

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

    explains technical terms and names

    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
    eers
    0.53
    fortun
    0.52
    e
    0.50
     να
    0.48
    face
    0.46
     navig
    0.45
     fichier
    0.45
     מח
    0.45
    дается
    0.45
    க்கோ
    0.45
    POSITIVE LOGITS
     Configuring
    0.53
     Inserting
    0.53
    ట్స్‌
    0.51
     అధ
    0.50
    áz
    0.48
     Removing
    0.46
     Internal
    0.46
     দিয়েই
    0.45
    ڑ
    0.44
     Tight
    0.44
    Activations Density 0.001%

    No Known Activations