© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46529
    Prev
    Next
    INDEX
    Explanations

    describing subsequent word

    np_acts-logits-general · gemini-2.5-flash-lite

    TypeError and non-numeric input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    觜
    0.52
    мани
    0.46
     список
    0.46
     CentOS
    0.45
     Département
    0.44
     fromi
    0.43
     wrześ
    0.41
     Promoter
    0.40
    行情
    0.40
     तोंड
    0.39
    POSITIVE LOGITS
    .”
    0.49
     nedeniyle
    0.48
     abbiamo
    0.47
    ':
    0.46
     dobbiamo
    0.46
    ⏲
    0.46
    !”
    0.45
     permite
    0.43
     Derek
    0.43
    オール
    0.42
    Activations Density 0.000%

    No Known Activations