© 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. 53-GEMMASCOPE-2-RES-262K
    7. 45985
    Prev
    Next
    INDEX
    Explanations

    Att words

    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_53_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
     Ат
    0.43
     wollten
    0.40
     нескольких
    0.40
     clickView
    0.39
     pisc
    0.38
    രാഷ്ട്ര
    0.38
     mehrere
    0.38
    孽
    0.37
     ATR
    0.37
     kisi
    0.37
    POSITIVE LOGITS
    ributions
    0.55
    ributor
    0.53
    ributive
    0.52
    RIBUTION
    0.51
    enu
    0.48
    ributed
    0.48
    ributing
    0.46
    RIBUT
    0.45
    ribut
    0.45
    ribu
    0.44
    Activations Density 0.002%

    No Known Activations