© 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-65K
    7. 2817
    Prev
    Next
    INDEX
    Explanations

    named entities and AI models

    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_65k_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
    s
    0.44
    6
    0.42
    4
    0.40
    8
    0.37
    if
    0.36
    7
    0.36
    5
    0.36
    ों
    0.34
    9
    0.33
    ч
    0.33
    POSITIVE LOGITS
     був
    0.36
     obtuvo
    0.35
     abbia
    0.34
     conhecida
    0.34
     preacher
    0.34
     apuesta
    0.34
     conhecido
    0.34
     njeg
    0.33
     şirk
    0.33
     ettevõ
    0.33
    Activations Density 0.146%

    No Known Activations