© 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. 11738
    Prev
    Next
    INDEX
    Explanations

    ordered lists of values

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

    tuple

    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
    薇
    0.48
     آتش
    0.47
     incênd
    0.46
    燎
    0.46
    ంబే
    0.46
    炽
    0.45
    ffiti
    0.45
    ন্যবাদ
    0.44
     moléculas
    0.44
     سرطان
    0.44
    POSITIVE LOGITS
     tuple
    1.38
    tuple
    1.26
     tuples
    1.18
     Tuple
    1.12
    Tuple
    1.10
    tuples
    0.93
     tup
    0.74
     Tu
    0.65
     tu
    0.64
     [(
    0.64
    Activations Density 0.001%

    No Known Activations