© 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. 140069
    Prev
    Next
    INDEX
    Explanations

    RSP NUTRITION

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

    Historical Argument

    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
    Negative Logits
     forêt
    0.52
     geográfica
    0.51
    志森
    0.45
     Modifier
    0.42
     znamená
    0.42
    ешь
    0.41
    اليه
    0.41
    binder
    0.41
    閻
    0.41
     irm
    0.40
    POSITIVE LOGITS
    pmatrix
    0.46
    anganese
    0.45
    derabad
    0.44
     اپنا
    0.44
    ]^{+}$
    0.43
    गण
    0.43
    雳
    0.43
    delta
    0.42
    ellen
    0.42
    django
    0.42
    Activations Density 0.000%

    No Known Activations