© 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. 156900
    Prev
    Next
    INDEX
    Explanations

    trash, rubbish, Nike

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

    without or indefinitely

    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
     PM
    0.53
     pm
    0.51
    PM
    0.47
    print
    0.45
    рина
    0.45
    0.45
    reira
    0.44
    י
    0.44
    reath
    0.44
    tric
    0.44
    POSITIVE LOGITS
     avaient
    0.50
     desgr
    0.49
     божомол
    0.49
     allait
    0.48
     termos
    0.47
     Passo
    0.47
     ongles
    0.47
     dispoz
    0.46
     regra
    0.46
     ogl
    0.46
    Activations Density 0.001%

    No Known Activations