© 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. 1389
    Prev
    Next
    INDEX
    Explanations

    character substitution

    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
     richiest
    0.51
     enanti
    0.48
     operands
    0.47
    㑔
    0.45
    好き
    0.42
    蒖
    0.42
    対流
    0.42
    患者
    0.41
     mesons
    0.41
    ूरती
    0.40
    POSITIVE LOGITS
     мате
    0.44
    }+\
    0.43
     جيم
    0.42
    }{
    0.42
    }
    0.42
     ט
    0.41
    0.41
     ي
    0.41
     програ
    0.41
     ಎರಡು
    0.41
    Activations Density 0.000%

    No Known Activations