© 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. 65820
    Prev
    Next
    INDEX
    Explanations

    pound, pounds, pounding, bond

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

    pounds or lb

    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
    𝚍
    0.59
    namespaces
    0.59
    не
    0.58
    dus
    0.58
    ým
    0.54
    ٧
    0.54
    datos
    0.53
     丿
    0.52
     discriminated
    0.52
     لأنه
    0.52
    POSITIVE LOGITS
     pound
    1.07
     Pound
    0.90
     pounds
    0.89
     pounding
    0.81
    pound
    0.77
    er
    0.70
     Pounds
    0.68
    पाउंड
    0.66
     pounded
    0.65
    ை
    0.64
    Activations Density 0.728%

    No Known Activations