© 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. 238516
    Prev
    Next
    INDEX
    Explanations

    relocation and cleaning services

    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
    는
    0.58
    은
    0.54
    2
    0.52
    :'],
    0.52
    7
    0.52
    נג
    0.50
    1
    0.50
     پیش
    0.48
    的三
    0.48
    は
    0.47
    POSITIVE LOGITS
    èvre
    0.49
     velké
    0.49
     mémoire
    0.49
     Afghans
    0.46
    ights
    0.46
    anians
    0.46
    sels
    0.45
     estadounidenses
    0.45
    burgo
    0.45
    ẹo
    0.44
    Activations Density 0.000%

    No Known Activations