© 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. 6891
    Prev
    Next
    INDEX
    Explanations

    status updates or voting

    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
    notation
    0.50
    晿
    0.50
     आरओ
    0.48
    }|$
    0.48
    formation
    0.47
    leigh
    0.46
    elif
    0.46
    ᓲ
    0.45
    figuration
    0.45
     Evaluation
    0.44
    POSITIVE LOGITS
     voted
    0.50
     dove
    0.49
     recited
    0.46
     residente
    0.44
     resident
    0.43
     doves
    0.43
     hunk
    0.42
     cinta
    0.42
     defaulted
    0.42
     mango
    0.42
    Activations Density 0.000%

    No Known Activations