© 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. 18959
    Prev
    Next
    INDEX
    Explanations

    tokens following the

    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
    髄
    0.53
    Ctrl
    0.49
     இன்
    0.47
    ❷
    0.46
    ürdig
    0.46
    ⟥
    0.46
    wegian
    0.46
    ❸
    0.45
    akses
    0.44
    <unused1093>
    0.44
    POSITIVE LOGITS
    터
    0.45
     Rural
    0.44
     getter
    0.43
    য়া
    0.42
    胶
    0.42
    cers
    0.41
     жидко
    0.40
    iap
    0.40
     Phenomen
    0.40
    ضة
    0.40
    Activations Density 0.001%

    No Known Activations