© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18552
    Prev
    Next
    INDEX
    Explanations

    chemicals, even

    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_31_width_262k_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
    valuation
    0.48
     campe
    0.46
     rho
    0.43
     profite
    0.43
     manage
    0.42
     tarif
    0.42
     empower
    0.42
    髏
    0.42
     playbook
    0.42
     merch
    0.41
    POSITIVE LOGITS
    chemicals
    0.50
     chemicals
    0.49
     even
    0.47
     এমনকি
    0.46
     навіть
    0.45
     Chemicals
    0.45
     Даже
    0.44
     حتی
    0.43
     इवन
    0.42
     bahkan
    0.41
    Activations Density 0.088%

    No Known Activations