© 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-65K
    7. 35867
    Prev
    Next
    INDEX
    Explanations

    loss decreasing in sync

    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_65k_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
     tracksuit
    0.49
    Gosudarstvennyj
    0.49
    妷
    0.48
    posaż
    0.46
    जी
    0.46
    bardziej
    0.46
    ContextHeader
    0.44
    StudentNo
    0.44
    μαι
    0.43
     новый
    0.43
    POSITIVE LOGITS
     the
    0.44
     The
    0.43
     forestry
    0.42
    ,
    0.41
     Coastal
    0.41
     la
    0.40
     monolayers
    0.40
     UNESCO
    0.40
    The
    0.39
    LA
    0.39
    Activations Density 0.000%

    No Known Activations