© 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. 21500
    Prev
    Next
    INDEX
    Explanations

    predictions and success

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

    relations and concepts

    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
    Ї
    0.49
    ivet
    0.44
     losses
    0.42
    ikel
    0.42
     dies
    0.42
     died
    0.41
    CTRL
    0.40
    ]>
    0.40
    DW
    0.39
    ι
    0.39
    POSITIVE LOGITS
     opportunità
    0.52
     HOURS
    0.49
     నగ
    0.48
    饼
    0.46
     নগর
    0.46
    avacanam
    0.44
     পুরস্কার
    0.44
     Gardening
    0.44
     पॉइंट्स
    0.44
     NOMBRE
    0.43
    Activations Density 0.000%

    No Known Activations