© 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. 53229
    Prev
    Next
    INDEX
    Explanations

    speed, calculating

    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
     Rankings
    0.51
     Foto
    0.46
    Ảnh
    0.45
     डिव
    0.45
     Ranking
    0.44
    廨
    0.44
     Have
    0.42
     Typ
    0.42
     Selling
    0.42
    黉
    0.42
    POSITIVE LOGITS
    ව
    0.50
    𝘄
    0.48
     скорость
    0.46
     velocidad
    0.45
    োম
    0.45
    ли
    0.44
    сти
    0.43
    쉬
    0.43
     me
    0.43
    cil
    0.42
    Activations Density 0.001%

    No Known Activations