© 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. 18009
    Prev
    Next
    INDEX
    Explanations

    structured text components

    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
    iót
    0.42
    htein
    0.42
    presas
    0.42
    মেন্ট
    0.41
    ác
    0.41
     გადა
    0.41
    Raquete
    0.40
    惨
    0.40
    াচ্ছে
    0.40
     estrés
    0.39
    POSITIVE LOGITS
     Recon
    0.47
    ]
    0.46
     русской
    0.44
     Installing
    0.42
     FAX
    0.42
     Sept
    0.41
     Links
    0.41
     Fries
    0.41
     They
    0.40
     Milk
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.