© 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. 186215
    Prev
    Next
    INDEX
    Explanations

    past perfect and present perfect tense

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

    yearsGiant PandaTravelPerformance enhancementskillsextension

    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
     earth
    0.54
     sails
    0.50
     {
    0.49
     sentences
    0.48
     characters
    0.47
    地址
    0.47
     pages
    0.46
     poems
    0.46
    વે
    0.45
     oceans
    0.45
    POSITIVE LOGITS
     подви
    0.46
    ifico
    0.45
    ReadOnly
    0.44
    brochen
    0.44
     ضرور
    0.43
    nard
    0.43
     REACT
    0.42
    𒊑
    0.42
    <0xBB>
    0.42
     あの
    0.42
    Activations Density 0.001%

    No Known Activations