© 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. 19042
    Prev
    Next
    INDEX
    Explanations

    specific entities and concepts

    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
    [*][[
    0.39
    */
    0.38
     anci
    0.38
    …</
    0.38
     televisi
    0.37
    †
    0.37
    ونکہ
    0.37
    </i>
    0.35
     ­
    0.35
    いたり
    0.35
    POSITIVE LOGITS
     MNIST
    0.49
     Pikachu
    0.48
     Ryanair
    0.47
    mnist
    0.47
     Thanos
    0.45
     Mavic
    0.44
     Deadpool
    0.42
     DQN
    0.42
     Figaro
    0.42
     Mayweather
    0.41
    Activations Density 0.171%

    No Known Activations