© 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. 155165
    Prev
    Next
    INDEX
    Explanations

    phrases starting with like, who, or allowed

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

    descriptive words followed by context

    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
     gdyż
    0.54
    because
    0.54
    เพราะ
    0.54
     karena
    0.50
     because
    0.49
     क्योंकि
    0.48
     porque
    0.46
    }.
    0.46
     omdat
    0.46
     ponieważ
    0.45
    POSITIVE LOGITS
    而言
    0.64
    *,
    0.57
    來說
    0.56
     ,
    0.55
    !,
    0.52
    %,
    0.51
    ®,
    0.50
    来看
    0.50
    **,
    0.50
    ™,
    0.49
    Activations Density 0.130%

    No Known Activations