© 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. 57105
    Prev
    Next
    INDEX
    Explanations

    billing and charges

    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
     funded
    -0.85
    afka
    -0.83
     scelta
    -0.81
     paid
    -0.80
    setNum
    -0.79
     paying
    -0.79
     כוס
    -0.77
    altezza
    -0.77
    になれる
    -0.75
     payout
    -0.75
    POSITIVE LOGITS
     charges
    2.47
     charged
    2.23
    charges
    2.22
     charge
    2.20
    Charges
    1.96
    charged
    1.85
    charge
    1.84
     Charges
    1.82
    Charged
    1.74
     Charged
    1.70
    Activations Density 0.030%

    No Known Activations