© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 210443
    Prev
    Next
    INDEX
    Explanations

    outcomes of actions

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

    Sometimes just

    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
     aort
    0.47
    alev
    0.47
     אמ
    0.46
     definitiv
    0.46
    OURCES
    0.44
    :"",
    0.44
     mij
    0.43
     مرت
    0.43
     العص
    0.42
    ধ্যার
    0.42
    POSITIVE LOGITS
    ところ
    0.51
     थोड़ी
    0.49
    のことを
    0.49
     disgruntled
    0.46
    文
    0.45
    いました
    0.45
     थोड़ी
    0.44
    様々な
    0.44
    ின்
    0.44
     जिन्होंने
    0.44
    Activations Density 0.000%

    No Known Activations