© 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. 48718
    Prev
    Next
    INDEX
    Explanations

    example is

    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
     )
    0.44
     )-
    0.41
     હત
    0.40
    jobj
    0.40
    ynb
    0.40
     ),
    0.39
    ristmas
    0.39
    ylate
    0.38
    𓈒
    0.38
    atoi
    0.38
    POSITIVE LOGITS
    থমে
    0.43
     त्यानुसार
    0.42
     அவற்றில்
    0.41
     अलग
    0.41
    ែង
    0.40
    VERE
    0.40
    ITIONAL
    0.39
     அவற்றை
    0.38
    ্যা
    0.38
     henne
    0.38
    Activations Density 0.000%

    No Known Activations