© 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. 225189
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific terms

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

    physical attributes and abstract fields

    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
     سایر
    0.49
    その他の
    0.48
    萏
    0.47
    "];
    0.45
    પ
    0.45
     Allgeme
    0.44
     التاس
    0.44
    displayText
    0.43
    尓
    0.43
     Donne
    0.43
    POSITIVE LOGITS
     sapphire
    0.50
     hydrodynamic
    0.46
    アウトドア
    0.46
     보니
    0.46
     sizes
    0.46
     tamaños
    0.45
     enlargement
    0.45
     alfalfa
    0.45
     silhouette
    0.44
     silica
    0.44
    Activations Density 0.000%

    No Known Activations