Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 247481
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <td>
    0.44
     temer
    0.41
                    
    0.40
     proffered
    0.40
    óra
    0.39
    ิว
    0.39
    也不会
    0.39
    opu
    0.39
     ticket
    0.38
     clums
    0.38
    POSITIVE LOGITS
     Techniques
    0.52
     मिळाल
    0.51
    ない
    0.50
     техника
    0.50
     Ở
    0.48
    風格
    0.48
     і
    0.48
     있다면
    0.47
     Ι
    0.46
     INSTALL
    0.46
    Activations Density 0.006%

    No Known Activations