© 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. 225080
    Prev
    Next
    INDEX
    Explanations

    may reach, artificial syndrome, file cabinet

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

    movement finishing

    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
    返し
    0.46
     derivable
    0.45
    せない
    0.44
    不利
    0.43
    ➥
    0.42
    なし
    0.41
    ர்ம
    0.41
    کول
    0.41
    ⃖
    0.41
    しない
    0.41
    POSITIVE LOGITS
     Family
    0.53
     Bil
    0.51
     His
    0.50
     Living
    0.50
     In
    0.49
     grandchildren
    0.49
     ayah
    0.49
     On
    0.49
     Financial
    0.48
     Groot
    0.48
    Activations Density 0.000%

    No Known Activations