© 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-16K
    7. 7175
    Prev
    Next
    INDEX
    Explanations

    but introducing alternatives

    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_16k_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
    ⇢
    0.38
    र्ने
    0.37
     developmentally
    0.37
    zyc
    0.36
     ਨਹੀਂ
    0.36
     алып
    0.35
     incubated
    0.34
     үч
    0.34
     மேற்கு
    0.34
     wybra
    0.34
    POSITIVE LOGITS
    </tbody>
    0.43
    emois
    0.42
     навіть
    0.41
     Truly
    0.41
    oubtedly
    0.40
     Isso
    0.40
     algum
    0.40
    也會
    0.40
     Anyways
    0.39
     Eventually
    0.39
    Activations Density 0.117%

    No Known Activations