© 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-65K
    7. 7182
    Prev
    Next
    INDEX
    Explanations

    percentage calculations

    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_65k_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
    Ö
    0.45
     had
    0.43
     headline
    0.43
     Esto
    0.42
     Ö
    0.41
     söz
    0.41
     Ó
    0.40
    ngram
    0.40
    와
    0.40
     permut
    0.39
    POSITIVE LOGITS
    Reserv
    0.46
    reservation
    0.45
    percent
    0.45
     réservation
    0.43
    glucose
    0.43
     Reservations
    0.42
    centage
    0.42
     valorem
    0.42
     आरक्षण
    0.41
    Reservation
    0.41
    Activations Density 0.004%

    No Known Activations