© 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. 152331
    Prev
    Next
    INDEX
    Explanations

    recognises excellence and rewards

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

    reward, growth, potential, threat

    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
     җиңү
    0.48
    િત
    0.47
    ແມ
    0.47
    醺
    0.45
     পর্দ
    0.45
    ம
    0.45
     это
    0.45
     ఉ
    0.45
     ஆர்வ
    0.45
    ்த
    0.44
    POSITIVE LOGITS
    p
    0.58
    لیفون
    0.48
    spiritual
    0.48
    input
    0.48
    text
    0.48
    treating
    0.48
    pathetic
    0.47
    puppet
    0.47
    pass
    0.46
    post
    0.46
    Activations Density 0.001%

    No Known Activations