© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13947
    Prev
    Next
    INDEX
    Explanations

    weights and values

    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
    τού
    0.48
    consc
    0.44
    evil
    0.41
    ᱜ
    0.40
    paragraphs
    0.40
    ᓛ
    0.39
    Gesellschaft
    0.39
    潸
    0.39
    intégr
    0.39
    planade
    0.39
    POSITIVE LOGITS
     weight
    0.93
     value
    0.89
    权重
    0.84
     weights
    0.81
     values
    0.76
     değeri
    0.75
     score
    0.73
     attributes
    0.73
     contribution
    0.72
     assigned
    0.70
    Activations Density 0.071%

    No Known Activations