© 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. 53311
    Prev
    Next
    INDEX
    Explanations

    training philosophy or process

    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
    Vous
    0.46
    кой
    0.45
     бывшего
    0.44
     remarque
    0.44
    यिक
    0.43
     उस
    0.42
    IMPLEMENT
    0.42
    弃
    0.42
    喺
    0.42
    ೆಂಟ್
    0.42
    POSITIVE LOGITS
    </i>
    0.45
    «.
    0.42
     transcendent
    0.41
     Bi
    0.40
    Bi
    0.40
     Zi
    0.40
    .»
    0.39
    }()
    0.39
    irs
    0.39
    itiers
    0.38
    Activations Density 0.008%

    No Known Activations