© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 40242
    Prev
    Next
    INDEX
    Explanations

    Language or specific terms

    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
     इसीलिए
    0.45
    \
    0.43
    intuitive
    0.42
    those
    0.42
    続ける
    0.42
    ]
    0.41
    VS
    0.40
    morale
    0.40
    racting
    0.40
    Democrats
    0.40
    POSITIVE LOGITS
     zdjęcie
    0.49
    绡
    0.49
    στημα
    0.47
    要把
    0.47
    рих
    0.47
     жен
    0.47
     осу
    0.47
     Fonbet
    0.46
     пары
    0.46
     সংযোগ
    0.46
    Activations Density 0.000%

    No Known Activations