© 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. 43013
    Prev
    Next
    INDEX
    Explanations

    privacy, head, institutions, sprout, toe, share, limes, cats

    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
    WEEN
    0.44
    +.
    0.42
     ज्ञ
    0.42
     மற்றும்
    0.42
     물론
    0.41
    もちろん
    0.41
     البته
    0.41
    )$
    0.39
    非常
    0.38
    双方
    0.38
    POSITIVE LOGITS
    acağına
    0.44
     haki
    0.43
    เกี่ยวข้อง
    0.42
     Adası
    0.41
    izal
    0.41
    itars
    0.40
    дії
    0.40
    ěr
    0.40
     accusations
    0.40
    öra
    0.39
    Activations Density 0.007%

    No Known Activations