© 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. 90190
    Prev
    Next
    INDEX
    Explanations

    decreased, Padma, convergent, abortion, necessary

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

    Alice, birds, recipe code

    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
    า
    0.49
    ों
    0.49
     kr
    0.47
    s
    0.47
    WOM
    0.47
    בוה
    0.47
    สำหรับ
    0.47
    รุ่น
    0.46
    ો
    0.45
     that
    0.45
    POSITIVE LOGITS
    uthers
    0.59
    hasClass
    0.44
    Unifier
    0.44
     অফিসের
    0.44
    नोई
    0.44
     شمار
    0.44
     പറയുന്നത്
    0.42
    നോ
    0.41
    ერს
    0.41
     ধারা
    0.41
    Activations Density 0.001%

    No Known Activations