© 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. 201547
    Prev
    Next
    INDEX
    Explanations

    service verification and requirements

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

    important considerations

    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
     மெட்ரோ
    0.48
     عوامی
    0.48
    ኞ
    0.44
    markets
    0.44
     اڈوں
    0.43
    唰
    0.43
    られている
    0.43
     मुबारक
    0.43
    㖣
    0.42
    Semitic
    0.42
    POSITIVE LOGITS
    ↵↵↵
    0.52
     ogni
    0.51
     alimentation
    0.51
     decreases
    0.50
     gama
    0.50
     determines
    0.50
     steeds
    0.50
     incroyable
    0.50
    </h2>
    0.49
     urine
    0.49
    Activations Density 0.000%

    No Known Activations