© 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-16K
    7. 11974
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

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

    forgiveness, planners, 'laadla'

    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_16k_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
    珺
    0.49
    ゐ
    0.46
    楡
    0.45
    嬰
    0.44
    終わ
    0.42
    量的
    0.42
    логи
    0.41
    舫
    0.41
    観察
    0.41
    პირ
    0.40
    POSITIVE LOGITS
    CHE
    0.52
    anées
    0.47
    ANE
    0.46
    ैश
    0.45
     bicarbonate
    0.45
     asistente
    0.45
     svega
    0.44
    ($"{
    0.44
    atas
    0.43
    apet
    0.43
    Activations Density 0.009%

    No Known Activations