© 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. 48827
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    forget intellectual honesty

    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
    fashioned
    0.54
    PDA
    0.51
    ਧੀ
    0.45
    xhtml
    0.45
    τυ
    0.43
    си
    0.43
    𝙿
    0.43
    pus
    0.42
    ਮੀ
    0.42
    produto
    0.41
    POSITIVE LOGITS
     panorama
    0.47
     historical
    0.46
     चारों
    0.45
     Sozial
    0.45
    燡
    0.45
     tous
    0.44
     Tib
    0.43
    做出
    0.43
    的他
    0.43
     Granny
    0.43
    Activations Density 0.000%

    No Known Activations