© 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. 51368
    Prev
    Next
    INDEX
    Explanations

    technical system descriptions

    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
    }</
    0.51
    Disconnect
    0.51
     সবসময়
    0.45
    Bri
    0.45
    常に
    0.43
     커
    0.42
    けん
    0.42
    )}')
    0.41
    Nunca
    0.41
    沖縄
    0.41
    POSITIVE LOGITS
     Administrative
    0.45
     Tissue
    0.44
     Sip
    0.44
     الوضع
    0.43
     Decl
    0.43
     Weed
    0.43
     Shaw
    0.43
     nisk
    0.42
     was
    0.42
     osa
    0.42
    Activations Density 0.006%

    No Known Activations