© 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-65K
    7. 13702
    Prev
    Next
    INDEX
    Explanations

    plays a

    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_65k_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
    М
    0.50
    *.
    0.47
    Turns
    0.47
    Мы
    0.46
     lounges
    0.46
    UNA
    0.45
     sinks
    0.45
    Зна
    0.44
     कहलाता
    0.44
    UN
    0.43
    POSITIVE LOGITS
     memastikan
    0.49
     ۴
    0.45
     đảm
    0.44
     особое
    0.43
    <unused2197>
    0.41
     pedagogical
    0.39
    _
    0.39
    astikan
    0.39
     குறிப்பாக
    0.39
     शहरातील
    0.39
    Activations Density 0.105%

    No Known Activations