© 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. 40-GEMMASCOPE-2-RES-262K
    7. 210325
    Prev
    Next
    INDEX
    Explanations

    leverages RAM and CPU

    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_40_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
    儩
    0.40
    渠
    0.39
     ඔ
    0.39
     Akadem
    0.39
    )}-
    0.38
    recovery
    0.38
     cuch
    0.38
     ብዙ
    0.38
     दीर्घ
    0.38
    腚
    0.37
    POSITIVE LOGITS
     prefers
    0.38
    grapes
    0.38
     Surveys
    0.38
     accrue
    0.37
     studied
    0.37
    iai
    0.37
     תק
    0.37
    𝕄
    0.37
    uniq
    0.37
     Middleware
    0.37
    Activations Density 0.001%

    No Known Activations