© 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-65K
    7. 723
    Prev
    Next
    INDEX
    Explanations

    acid, sand, web, likes

    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_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
     laborious
    0.48
     qualify
    0.47
     computers
    0.46
    Eligibility
    0.44
     authorise
    0.44
    niger
    0.43
    igné
    0.42
    蒨
    0.41
     libra
    0.41
     hairstyles
    0.41
    POSITIVE LOGITS
    <0xE2>
    0.45
     अतुल
    0.44
    >>
    0.43
    ch
    0.43
    parsed
    0.43
     нарко
    0.43
     उड़ान
    0.42
     здоро
    0.42
     দখ
    0.42
    cccnc
    0.42
    Activations Density 0.000%

    No Known Activations