© 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-16K
    7. 161
    Prev
    Next
    INDEX
    Explanations

    If, what, then, into

    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
     hostess
    0.24
     proposal
    0.23
     khen
    0.22
     proposals
    0.22
     décret
    0.21
     biết
    0.21
    >());
    0.21
     harmonization
    0.21
    NotBlank
    0.21
    dV
    0.21
    POSITIVE LOGITS
     Якщо
    0.30
    Якщо
    0.27
     Antônio
    0.27
    ߋ
    0.27
     Você
    0.26
    蟶
    0.26
    𝐖
    0.25
     क्योंकि
    0.25
    𝓪
    0.25
    ције
    0.25
    Activations Density 0.001%

    No Known Activations