© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 169898
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

    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
    Más
    0.47
    SCHRAMM
    0.47
    ર
    0.46
    מע
    0.45
    ర్థ
    0.45
    Bạn
    0.45
     elucidate
    0.45
     superconductors
    0.45
    ರ
    0.44
    ፃ
    0.43
    POSITIVE LOGITS
    present
    0.48
     Municip
    0.45
    umos
    0.44
    one
    0.44
    apo
    0.44
     Larg
    0.43
    apag
    0.43
     Purch
    0.43
     बोलने
    0.43
     배치
    0.43
    Activations Density 0.001%

    No Known Activations