© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 34693
    Prev
    Next
    INDEX
    Explanations

    adding or assigning results

    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_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
    Baz
    0.39
    齁
    0.39
    ቖ
    0.38
    Hip
    0.37
    𝔬
    0.37
    $<
    0.37
    Does
    0.36
    chitz
    0.36
    }.$$
    0.36
    Violation
    0.36
    POSITIVE LOGITS
     addTo
    0.52
    addTo
    0.47
    ToAdd
    0.45
    添加到
    0.44
     addition
    0.43
    appendTo
    0.41
     contributed
    0.39
    AddTo
    0.39
     added
    0.38
     items
    0.37
    Activations Density 0.093%

    No Known Activations