© 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. 40-GEMMASCOPE-2-RES-262K
    7. 190863
    Prev
    Next
    INDEX
    Explanations

    unspoken tension

    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_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
     Ising
    0.43
    ğer
    0.43
    Cntr
    0.43
    {\
    0.41
     Medicines
    0.41
     extensible
    0.40
    qPCR
    0.40
     Arten
    0.40
     types
    0.40
     Pois
    0.39
    POSITIVE LOGITS
     వరు
    0.40
    TOOL
    0.38
     вопро
    0.38
     undisclosed
    0.38
     unatt
    0.37
    OKE
    0.37
     đâu
    0.36
     bygone
    0.35
     ठ
    0.35
     ?:
    0.35
    Activations Density 0.000%

    No Known Activations