© 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. 43024
    Prev
    Next
    INDEX
    Explanations

    impartial journalism

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

    sections, lists, or numbered points

    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
     DIFFERENT
    0.58
     رفض
    0.53
    \})
    0.48
     некоторым
    0.47
     স্বামীর
    0.46
     चर्चे
    0.46
    જે
    0.45
    所有人
    0.45
     DIRECT
    0.44
    berapa
    0.44
    POSITIVE LOGITS
     jezika
    0.48
     scienza
    0.44
     mains
    0.44
     tradiz
    0.43
    洟
    0.43
     maturation
    0.42
     brinc
    0.42
     ternary
    0.41
     meshes
    0.40
     blanchâtre
    0.40
    Activations Density 0.000%

    No Known Activations