© 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. 72629
    Prev
    Next
    INDEX
    Explanations

    not prohibit actions

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

    automated practices

    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
     \&
    0.58
     př
    0.50
    邃
    0.49
     posiad
    0.48
     reik
    0.47
    𝓢
    0.46
    חר
    0.46
     or
    0.45
    াপি
    0.45
    ál
    0.45
    POSITIVE LOGITS
     వివా
    0.49
    ilidade
    0.47
     таъ
    0.44
    ukone
    0.44
     ठहरा
    0.41
     اساس
    0.41
    )、
    0.40
     stripper
    0.40
     comply
    0.40
    uchtigkeit
    0.40
    Activations Density 0.002%

    No Known Activations