© 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. 73840
    Prev
    Next
    INDEX
    Explanations

    rental, hygiene, attire

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

    ownership, claims, effort, credibility, exclusivity, aspirational, aggressive, value, relationship, renting

    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
    锤
    0.48
    Initialize
    0.47
    俱乐
    0.46
    erne
    0.46
    蓦
    0.46
    inä
    0.46
    avaju
    0.45
    了两
    0.45
    퍽
    0.45
     확률
    0.45
    POSITIVE LOGITS
     rental
    0.61
     bacteria
    0.52
     higiene
    0.51
     Rental
    0.51
    rental
    0.47
     hygiene
    0.46
     attire
    0.46
     shaved
    0.46
     foodstuffs
    0.45
     rented
    0.45
    Activations Density 0.003%

    No Known Activations