© 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. 46656
    Prev
    Next
    INDEX
    Explanations

    email addresses and planning lists

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

    data_ created, gastroenteritis, Reading a

    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
     বার্তা
    0.46
    nač
    0.44
     Reichs
    0.42
     valde
    0.42
    ní
    0.41
     მდ
    0.41
    </b>
    0.41
     Configur
    0.41
     Kraj
    0.41
    utti
    0.40
    POSITIVE LOGITS
    ithmet
    0.45
    shoes
    0.39
    डान
    0.39
    ahay
    0.38
    ቆዳ
    0.38
    Blurred
    0.38
    ৪৯
    0.38
    રોના
    0.37
     館
    0.37
    蚱
    0.37
    Activations Density 0.000%

    No Known Activations