© 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. 31-GEMMASCOPE-2-RES-16K
    7. 2636
    Prev
    Next
    INDEX
    Explanations

    explaining or predicting

    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_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
    Lastly
    0.35
    最后
    0.32
     lastly
    0.32
    twin
    0.32
     最后
    0.32
    ignet
    0.31
    只
    0.31
    所有
    0.30
     niveles
    0.30
     सभी
    0.30
    POSITIVE LOGITS
     explic
    0.42
     explanatory
    0.41
     ambivalent
    0.39
     Explain
    0.38
     falsehood
    0.38
     explain
    0.38
     debunk
    0.36
     nonchal
    0.36
     expliqué
    0.36
     beispielsweise
    0.36
    Activations Density 0.337%

    No Known Activations