© 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. 199129
    Prev
    Next
    INDEX
    Explanations

    production, film, mill, copyright

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

    phrases starting with main verbs or nouns

    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
    च्युअल
    0.56
    rí
    0.54
    रियल
    0.52
     આવશે
    0.52
     आलेल्या
    0.52
    ल्यू
    0.50
    ान्स
    0.50
    lée
    0.50
    Მ
    0.50
    lapping
    0.49
    POSITIVE LOGITS
     danno
    0.49
     fut
    0.46
    CONDS
    0.41
     vac
    0.41
    становление
    0.39
    boi
    0.38
    を
    0.38
    FXML
    0.38
     ecuaciones
    0.38
    ﻟ
    0.38
    Activations Density 0.000%

    No Known Activations