© 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. 225482
    Prev
    Next
    INDEX
    Explanations

    body positive

    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
     जटिल
    0.50
     Routledge
    0.48
    ্দ
    0.46
    ન
    0.46
     ลักษณะ
    0.45
    交換
    0.45
    <unused1086>
    0.45
    সহ
    0.44
     Unlike
    0.44
    ន្ថ
    0.43
    POSITIVE LOGITS
     pecinta
    0.52
     formée
    0.45
     negar
    0.43
     positif
    0.43
     positivo
    0.42
    URN
    0.42
    toBytes
    0.42
     religi
    0.41
     possibili
    0.41
     qualific
    0.41
    Activations Density 0.000%

    No Known Activations