© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117738
    Prev
    Next
    INDEX
    Explanations

    LD followed by specific initialisms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     רב
    -0.76
     hearers
    -0.71
     socialization
    -0.70
    wole
    -0.69
     Futures
    -0.68
     incontinence
    -0.68
     tiers
    -0.67
     untreated
    -0.67
    fot
    -0.66
     ashamed
    -0.65
    POSITIVE LOGITS
     LD
    1.32
    LD
    1.08
     ld
    0.94
     Ledger
    0.86
     Ld
    0.86
     qualcosa
    0.79
     Ladd
    0.79
     LDA
    0.78
     Lad
    0.77
     LAD
    0.77
    Activations Density 0.035%

    No Known Activations