© 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. 135
    Prev
    Next
    INDEX
    Explanations

    religious/political figures and related concepts

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

    magazine` `cover` `rocket` `

    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
    শ
    0.49
    以上
    0.47
    auks
    0.47
    北京
    0.46
    arkhand
    0.46
    ärten
    0.44
    上面
    0.44
    ǎng
    0.44
    ijas
    0.43
    ನೇ
    0.43
    POSITIVE LOGITS
    6
    0.52
    Dent
    0.51
    often
    0.49
    PAD
    0.46
    volved
    0.46
    ecode
    0.46
    B
    0.46
    o
    0.45
    5
    0.45
     scint
    0.45
    Activations Density 0.000%

    No Known Activations