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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6708
    Prev
    Next
    INDEX
    Explanations

    languages from various regions

    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
     to
    0.37
    3
    0.34
    4
    0.27
     that
    0.27
     Which
    0.27
    9
    0.27
    6
    0.27
     Doesn
    0.26
    1
    0.26
    _
    0.26
    POSITIVE LOGITS
    นาะ
    0.25
     către
    0.25
     사람
    0.24
    ಿಸಬಹುದು
    0.24
    जनबी
    0.24
    ὴν
    0.24
     온라인
    0.24
     beginnetje
    0.24
    ėje
    0.24
     인터넷
    0.23
    Activations Density 0.017%

    No Known Activations