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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 26363
    Prev
    Next
    INDEX
    Explanations

    offer self-skills

    np_acts-logits-general · gemini-2.5-flash-lite

    I am

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     любого
    0.60
     второго
    0.53
     інших
    0.50
    サービスの
    0.49
    堬
    0.49
    客户
    0.48
    顾客
    0.47
    任务
    0.46
     клиен
    0.46
     других
    0.45
    POSITIVE LOGITS
     heard
    0.46
     country
    0.46
    dc
    0.45
    been
    0.45
    န
    0.45
    dark
    0.44
     cenário
    0.43
     zin
    0.42
     PFAS
    0.42
     elixir
    0.42
    Activations Density 0.002%

    No Known Activations