© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 180830
    Prev
    Next
    INDEX
    Explanations

    religious or legal texts

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

    human experiences and characteristics

    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
    L
    0.49
     prompts
    0.44
    탈
    0.44
    A
    0.44
    j
    0.44
    렇
    0.43
    Fragment
    0.42
    .
    0.42
    런
    0.42
    Seats
    0.42
    POSITIVE LOGITS
     સરકાર
    0.67
     Direito
    0.58
     स्वच्छता
    0.57
     விவசாய
    0.54
     कर्मियों
    0.54
     fièvre
    0.53
     Constituição
    0.53
     zemlji
    0.53
     साप्ताहिक
    0.53
     कामकाजी
    0.53
    Activations Density 0.000%

    No Known Activations