© 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. 211489
    Prev
    Next
    INDEX
    Explanations

    meeting and appraisals

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

    list of specific terms

    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
    gramModel
    0.50
    协作
    0.48
    綗
    0.46
    یک
    0.46
     ständig
    0.45
    ىر
    0.44
     centrifuged
    0.44
    direccion
    0.44
     limites
    0.43
     রিলিফ
    0.43
    POSITIVE LOGITS
     alchemy
    0.49
     -
    0.47
     Amino
    0.46
     herbs
    0.44
     Ι
    0.43
     поко
    0.43
     CLASS
    0.43
     博
    0.42
    秦
    0.42
     prawns
    0.42
    Activations Density 0.001%

    No Known Activations