© 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. 71113
    Prev
    Next
    INDEX
    Explanations

    linking speech

    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
    hombre
    0.43
    uron
    0.42
    foe
    0.41
    ટ
    0.41
    video
    0.41
    lof
    0.41
    clare
    0.40
    ുണ്ട്
    0.40
    male
    0.39
    comfort
    0.39
    POSITIVE LOGITS
    :
    0.56
     prilikom
    0.54
    ;
    0.54
     khi
    0.54
     durante
    0.52
     όταν
    0.52
     عن
    0.52
     ketika
    0.50
     quando
    0.50
     →
    0.50
    Activations Density 0.013%

    No Known Activations