© 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. 65041
    Prev
    Next
    INDEX
    Explanations

    business projects

    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
     جميلة
    0.46
     சமூக
    0.45
     Unterschiede
    0.45
     कुठे
    0.43
     ऑनलाइन
    0.43
    โ
    0.41
    オ
    0.40
    anz
    0.40
     Bike
    0.40
    𝘥
    0.40
    POSITIVE LOGITS
     фор
    0.50
     xâm
    0.48
     compagnies
    0.44
     chevaux
    0.43
     executors
    0.43
     необходимо
    0.43
     φορ
    0.42
     дату
    0.41
     tzv
    0.40
     tasked
    0.40
    Activations Density 0.015%

    No Known Activations