© 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. 9483
    Prev
    Next
    INDEX
    Explanations

    llama and Google AI

    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
    쯜
    0.47
    ართველოს
    0.46
    ুয়াল
    0.46
    訸
    0.44
    ༡
    0.43
    ција
    0.43
    ębior
    0.42
    芘
    0.42
    Становништво
    0.42
     गिरि
    0.42
    POSITIVE LOGITS
     convex
    0.52
     protruding
    0.51
     longitudinal
    0.50
     unfolded
    0.50
     thickened
    0.50
     evenly
    0.50
     неболь
    0.49
     nozzles
    0.49
     dense
    0.48
     tightly
    0.48
    Activations Density 0.007%

    No Known Activations