© 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. 157663
    Prev
    Next
    INDEX
    Explanations

    conjuncts and prepositions

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

    acknowledging raw truth and consequences

    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
    Б
    0.54
    Ф
    0.50
    Ř
    0.49
    《
    0.48
    𝙄
    0.48
    Č
    0.48
    Ра
    0.48
    Д
    0.47
    ⴼ
    0.46
    Р
    0.46
    POSITIVE LOGITS
     hasn
    0.58
     clasp
    0.50
     provocation
    0.48
     clarifications
    0.46
     fence
    0.46
     buffet
    0.46
     che
    0.45
     grappling
    0.45
     itself
    0.45
     has
    0.44
    Activations Density 0.002%

    No Known Activations