© 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. 152678
    Prev
    Next
    INDEX
    Explanations

    offers secure checkout

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

    awareness of self and existence

    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
     was
    0.46
     sowohl
    0.44
     Ras
    0.43
     fet
    0.43
     Muskel
    0.43
    でした
    0.42
    兩
    0.42
    變
    0.40
    သွ
    0.40
     z
    0.39
    POSITIVE LOGITS
    ifiers
    0.50
     Tulum
    0.47
     suficientemente
    0.47
    ćeg
    0.47
    펭
    0.46
     Astros
    0.44
    测评
    0.44
     пространство
    0.43
     substituents
    0.43
    лло
    0.43
    Activations Density 0.001%

    No Known Activations