© 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. 77300
    Prev
    Next
    INDEX
    Explanations

    technical tools and platforms

    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
     museo
    0.59
     conçu
    0.57
     énorm
    0.54
     খুবই
    0.54
     boosting
    0.54
     पोकेमॉन
    0.54
     diseñada
    0.53
    ᠯ
    0.53
     Tint
    0.53
     concetto
    0.53
    POSITIVE LOGITS
     (
    0.49
    ,
    0.47
    )$
    0.46
    MES
    0.46
    0
    0.44
    No
    0.43
    CRO
    0.42
    ни
    0.41
    гда
    0.41
    0.41
    Activations Density 0.001%

    No Known Activations