© 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. 52456
    Prev
    Next
    INDEX
    Explanations

    from above

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

    car ownership or brands

    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
    šla
    0.57
    šli
    0.53
    cil
    0.52
     요즘
    0.48
     괜찮
    0.45
     fácil
    0.45
    ਸੀ
    0.45
    č
    0.45
    ú
    0.44
    uzten
    0.44
    POSITIVE LOGITS
     Symph
    0.52
     Jeter
    0.52
     Molecular
    0.51
     Depth
    0.50
     Pork
    0.50
     Shelley
    0.50
     Interrupt
    0.50
     Degrees
    0.50
     Antoine
    0.50
     Sei
    0.49
    Activations Density 0.000%

    No Known Activations