© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10271
    Prev
    Next
    INDEX
    Explanations

    inside or outside

    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_16k_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
     ಆದ್ದರಿಂದ
    0.40
    drugs
    0.40
    shape
    0.38
    shima
    0.38
    doc
    0.36
     undergo
    0.36
    laus
    0.36
    }|^{
    0.36
     astring
    0.36
    feas
    0.36
    POSITIVE LOGITS
    Inside
    0.81
     inside
    0.75
    inside
    0.64
     Inside
    0.64
     of
    0.57
     داخل
    0.55
     ভিতরে
    0.49
     Insider
    0.47
    Insider
    0.46
    威尔
    0.46
    Activations Density 0.043%

    No Known Activations