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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54959
    Prev
    Next
    INDEX
    Explanations

    drag formula down

    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
     advisory
    0.43
     dated
    0.43
    적
    0.43
     मानता
    0.43
     Advis
    0.42
     department
    0.41
     counsell
    0.41
     discussion
    0.40
    dated
    0.40
     eukary
    0.40
    POSITIVE LOGITS
    觕
    0.44
     hingga
    0.42
     إلي
    0.42
    antum
    0.39
     straks
    0.39
     Núñez
    0.39
     hasilnya
    0.39
    át
    0.38
     upang
    0.38
    新的
    0.38
    Activations Density 0.001%

    No Known Activations