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. 14704
    Prev
    Next
    INDEX
    Explanations

    i have 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_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
     accelerators
    0.42
     berühm
    0.41
    ólicos
    0.41
     nhiên
    0.40
    囔
    0.39
     brukes
    0.38
     śmier
    0.38
     effekt
    0.38
    కి
    0.38
     emplea
    0.37
    POSITIVE LOGITS
    ปัญหา
    0.53
     been
    0.50
    𝒃
    0.49
    problem
    0.49
    been
    0.47
    問題を
    0.45
    ashed
    0.43
    既存
    0.42
     problem
    0.42
    𝒂
    0.42
    Activations Density 0.024%

    No Known Activations