© 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. 40-GEMMASCOPE-2-RES-262K
    7. 98799
    Prev
    Next
    INDEX
    Explanations

    citations and references

    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_40_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
     counselors
    0.40
    銖
    0.39
    施行
    0.39
    修为
    0.38
    orus
    0.38
     resided
    0.38
     counselor
    0.38
    锈
    0.37
    fish
    0.37
    studentRecord
    0.36
    POSITIVE LOGITS
     criticise
    0.44
     secondary
    0.43
     prioritise
    0.43
     Secondary
    0.42
    чете
    0.41
     Jug
    0.41
     Palash
    0.41
     Jarvis
    0.41
     minimise
    0.41
     Transformer
    0.40
    Activations Density 0.007%

    No Known Activations