© 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-262K
    7. 2229
    Prev
    Next
    INDEX
    Explanations

    numbers and code delimiters

    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
     Clín
    0.33
    烜
    0.32
    ANGMAR
    0.31
    줘
    0.29
    義
    0.29
    バイ
    0.28
    AGUE
    0.28
    PAUL
    0.28
    処
    0.28
    ברה
    0.27
    POSITIVE LOGITS
     />
    0.32
    ></
    0.32
    }.
    0.31
     ;
    0.30
    ukasz
    0.29
     букмекерлар
    0.29
     利用
    0.28
    };
    0.28
     zelfs
    0.28
     daniel
    0.28
    Activations Density 0.594%

    No Known Activations