© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13533
    Prev
    Next
    INDEX
    Explanations

    brainstorm and clarify

    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
     όλ
    0.34
    щото
    0.32
     homeschooling
    0.31
     их
    0.31
     territory
    0.31
    誊
    0.31
    ssä
    0.30
     homeschool
    0.30
     Newsom
    0.30
     Roja
    0.30
    POSITIVE LOGITS
    。
    0.45
    }$.
    0.39
    }\
    0.37
    '};
    0.37
     achats
    0.37
    nın
    0.36
     மற்றும்
    0.36
     usługi
    0.36
     شركات
    0.34
     equipos
    0.34
    Activations Density 0.139%

    No Known Activations