© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 21854
    Prev
    Next
    INDEX
    Explanations

    explaining a problem or question

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     گی۔
    0.46
    INTEGER
    0.41
    %).
    0.41
    $/.
    0.40
    こちらも
    0.40
    ಶ
    0.39
     জন্যও
    0.38
    世紀
    0.38
    ಿಸಿದ್ದರು
    0.38
    களில்
    0.38
    POSITIVE LOGITS
    ：
    0.63
    ？
    0.49
     Basically
    0.48
     básicamente
    0.47
     basically
    0.47
    beis
    0.45
     består
    0.44
    ؟
    0.44
     মূলত
    0.44
    ❓
    0.43
    Activations Density 0.127%

    No Known Activations