© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 100050
    Prev
    Next
    INDEX
    Explanations

    origin and updates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ૨
    0.51
    comm
    0.44
    ifferentiated
    0.41
    ágina
    0.39
    util
    0.39
    esi
    0.39
    ீடு
    0.39
    矾
    0.38
    국의
    0.38
    เวณ
    0.38
    POSITIVE LOGITS
     Vodafone
    0.55
     escrever
    0.50
     enkel
    0.49
     Single
    0.48
     العمل
    0.47
     Arbeiten
    0.47
     contabil
    0.45
    lungen
    0.45
     какая
    0.45
    macher
    0.44
    Activations Density 0.000%

    No Known Activations