© 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. 40-GEMMASCOPE-2-RES-262K
    7. 17828
    Prev
    Next
    INDEX
    Explanations

    potential or future possibilities

    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_40_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
    Fmat
    0.44
    ವುದು
    0.44
     inconvén
    0.43
     বহুম
    0.39
    ረጥ
    0.39
    氅
    0.39
    วก
    0.38
    ﹂
    0.38
    äure
    0.38
     denominated
    0.38
    POSITIVE LOGITS
     potential
    1.14
    potential
    1.14
     Potential
    1.06
     pending
    1.05
     potencial
    1.03
    Potential
    1.03
    潜力
    1.02
     potenciales
    1.02
     prospective
    1.02
     потенциа
    0.99
    Activations Density 0.026%

    No Known Activations