© 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. 8453
    Prev
    Next
    INDEX
    Explanations

    direct and indirect

    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
    ون
    1.12
    ಮ
    1.09
    يد
    1.07
    0
    1.00
    িল
    0.94
    oe
    0.91
    ě
    0.91
    ги
    0.91
     wurden
    0.89
    og
    0.87
    POSITIVE LOGITS
     direct
    1.56
    direct
    1.38
     Direct
    1.38
     directa
    1.27
     directe
    1.20
    i
    1.16
    s
    1.10
    Direct
    1.09
     bezpośred
    1.02
     прямой
    1.02
    Activations Density 0.086%

    No Known Activations