© 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. 11841
    Prev
    Next
    INDEX
    Explanations

    country codes to names

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

    Forth stack operations

    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
    Finn
    0.34
    Resume
    0.34
    Ukraine
    0.33
    包裹
    0.33
    creens
    0.33
    म्मत
    0.32
    erequisites
    0.32
    **(
    0.32
    сії
    0.32
     বিধান
    0.32
    POSITIVE LOGITS
    肺
    0.38
     glomerul
    0.37
     malignancies
    0.36
    免疫
    0.34
     pathologies
    0.33
     Pulmonary
    0.33
     chronic
    0.33
     पीडीएफ
    0.33
     пато
    0.33
     coordonnées
    0.33
    Activations Density 0.000%

    No Known Activations