© 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. 24318
    Prev
    Next
    INDEX
    Explanations

    qualities of competence

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

    neural network generator

    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
     Dorset
    0.47
    ței
    0.47
    Dart
    0.46
    ق
    0.46
     Betting
    0.45
    Hollywood
    0.45
    у
    0.45
    чи
    0.44
    و
    0.44
    }:
    0.44
    POSITIVE LOGITS
     definitively
    0.55
     kurze
    0.51
    処
    0.51
     manipulative
    0.50
     idol
    0.50
     vaguely
    0.49
     docile
    0.48
     federally
    0.48
    +](=
    0.48
     logically
    0.48
    Activations Density 0.000%

    No Known Activations