© 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. 199401
    Prev
    Next
    INDEX
    Explanations

    mother's love

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

    benefit themselves or survive

    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
    Manus
    0.53
    Rad
    0.47
    Cons
    0.47
    ,
    0.47
    Defer
    0.44
    Alabama
    0.44
     clergy
    0.44
     isol
    0.44
     nas
    0.43
     Rad
    0.43
    POSITIVE LOGITS
     Только
    0.54
     ಪ್ರಯೋಜನ
    0.54
     পাঁচটি
    0.52
     帽
    0.52
     ძალი
    0.52
     Electrons
    0.50
    <unused86>
    0.50
     parvenir
    0.50
     දී
    0.50
     faible
    0.49
    Activations Density 0.000%

    No Known Activations