© 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. 129523
    Prev
    Next
    INDEX
    Explanations

    legal counsel

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

    diverging interests, IoT devices, installed antivirus

    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
    ides
    0.51
     preferable
    0.48
     dequeue
    0.48
    determined
    0.48
    考え
    0.48
    𝚒
    0.48
    devel
    0.47
     reiterate
    0.47
     constitut
    0.47
    ileged
    0.46
    POSITIVE LOGITS
     Counseling
    0.46
     Cada
    0.46
    PARAMS
    0.44
    </td>
    0.44
    ْ
    0.43
    వా
    0.43
    ונות
    0.42
    كي
    0.42
    ِ
    0.42
     مدار
    0.42
    Activations Density 0.000%

    No Known Activations