© 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. 178781
    Prev
    Next
    INDEX
    Explanations

    financial and specific terms

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

    instructions and how-to guides

    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
     dimanche
    0.44
     https
    0.43
    ับ
    0.43
     www
    0.41
     samedi
    0.41
     নীচে
    0.41
     शनिवार
    0.41
    <0xB3>
    0.41
    ในปี
    0.40
     पढ़िए
    0.40
    POSITIVE LOGITS
    つ
    0.49
    budget
    0.47
    dept
    0.47
    iring
    0.47
    cancel
    0.45
    brothers
    0.45
    Through
    0.45
    parents
    0.45
    cuando
    0.44
     पसंद
    0.44
    Activations Density 0.001%

    No Known Activations