© 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. 247393
    Prev
    Next
    INDEX
    Explanations

    getting lost

    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
    ilig
    0.54
    ்தான்
    0.54
    ศัก
    0.52
    ုန်
    0.52
     नव्ह
    0.52
    穫
    0.51
    ılması
    0.50
    це
    0.49
    ౪
    0.48
    ையில்
    0.48
    POSITIVE LOGITS
    ERG
    0.45
    ARR
    0.44
     uncond
    0.44
    f
    0.44
     Autor
    0.44
     unobstructed
    0.44
     emitted
    0.44
     autor
    0.43
     carpenters
    0.43
     COND
    0.43
    Activations Density 0.000%

    No Known Activations