© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 52609
    Prev
    Next
    INDEX
    Explanations

    dates, price, expiration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ರುವುದರಿಂದ
    0.49
     పి
    0.43
    ുവരി
    0.43
    ጂ
    0.41
     এডিনবার্গ
    0.40
     Unterschiede
    0.40
    निवेश
    0.39
    赓
    0.39
    ട്ട
    0.38
     আস্থা
    0.38
    POSITIVE LOGITS
     isotropic
    0.38
     suffering
    0.36
     carnival
    0.36
    QUES
    0.35
     sor
    0.35
     TR
    0.35
     пар
    0.35
    앓
    0.35
     из
    0.34
     relating
    0.34
    Activations Density 0.001%

    No Known Activations