© 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. 164885
    Prev
    Next
    INDEX
    Explanations

    password. to

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

    GPON, hemocyanin, Isolation Forest

    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
    r
    0.56
    t
    0.55
    ین
    0.51
    Ethereum
    0.50
    တ်
    0.50
    КИ
    0.49
    æ
    0.49
    ⿸
    0.48
    Province
    0.48
    Ram
    0.48
    POSITIVE LOGITS
     begr
    0.48
     सैकड़ों
    0.47
     heterod
    0.47
     domine
    0.47
     inget
    0.46
     monumento
    0.45
     worsened
    0.45
     disproportion
    0.44
     lässt
    0.44
     inkl
    0.43
    Activations Density 0.000%

    No Known Activations