© 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. 18939
    Prev
    Next
    INDEX
    Explanations

    section markers

    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
     ();
    0.44
    जिसे
    0.43
     ever
    0.38
     (),
    0.37
     likeness
    0.37
    俦
    0.36
     stanovnika
    0.36
     świecie
    0.35
     regex
    0.35
     depois
    0.35
    POSITIVE LOGITS
     Органи
    0.42
     فعل
    0.40
    Princ
    0.40
     заключается
    0.38
    subsection
    0.38
    Radi
    0.38
    Northern
    0.37
    <em>
    0.37
    subsubsection
    0.37
     горя
    0.36
    Activations Density 0.011%

    No Known Activations