© 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. 17510
    Prev
    Next
    INDEX
    Explanations

    form patterns with 'b'

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

    sin and cos in rotations

    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
     rada
    0.41
    zeniu
    0.39
     Dezember
    0.39
    㗆
    0.39
     стадии
    0.39
     پوکر
    0.38
     ঘটতে
    0.38
     Olimp
    0.38
     Huyền
    0.38
     manto
    0.38
    POSITIVE LOGITS
    strictly
    0.37
    aper
    0.35
     있고
    0.35
    ங்குக
    0.35
    ongs
    0.34
    KeyPressed
    0.34
    평
    0.34
    tere
    0.34
    αλ
    0.33
    pert
    0.33
    Activations Density 0.000%

    No Known Activations