© 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. 9459
    Prev
    Next
    INDEX
    Explanations

    variety of and Browder

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

    saying yes

    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
    இந்
    0.39
    Após
    0.37
     Dieser
    0.36
    ఙ
    0.36
     Stylish
    0.36
    Bitte
    0.35
    Согласно
    0.35
     deberá
    0.34
    ]."
    0.34
    Attr
    0.34
    POSITIVE LOGITS
     굉장히
    0.58
     väldigt
    0.58
     আজকে
    0.54
     ahorita
    0.53
     veldig
    0.51
     nagyon
    0.49
     خیلی
    0.49
     yeah
    0.48
     veľmi
    0.48
    ですよね
    0.48
    Activations Density 0.032%

    No Known Activations