© 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. 16-GEMMASCOPE-2-RES-262K
    7. 142188
    Prev
    Next
    INDEX
    Explanations

    test and driving

    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_16_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
     ammon
    0.55
     scammers
    0.52
     ofens
    0.51
     pointing
    0.50
     poisoned
    0.49
     subfamily
    0.48
    蟎
    0.47
     scritt
    0.46
    殳
    0.46
    哌
    0.46
    POSITIVE LOGITS
    ؟
    0.45
     Figures
    0.44
     Figure
    0.42
    imitives
    0.42
    ")
    0.41
     যাচাই
    0.41
     фигур
    0.41
    ')
    0.41
     figured
    0.41
     Accessibility
    0.41
    Activations Density 0.001%

    No Known Activations