© 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. 28212
    Prev
    Next
    INDEX
    Explanations

    altering predictions and timelines

    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
    benzoimidazole
    0.53
    startY
    0.46
     тобто
    0.45
     quelquefois
    0.43
    SecurityMarks
    0.43
    feeling
    0.42
     straining
    0.42
    ਤ
    0.42
    alaikums
    0.42
     जले
    0.41
    POSITIVE LOGITS
     Circuit
    0.58
     Technical
    0.52
     Open
    0.50
     Be
    0.49
     Support
    0.48
     De
    0.48
     Well
    0.48
     Cancer
    0.47
     Zu
    0.47
     Stewardship
    0.47
    Activations Density 0.007%

    No Known Activations