© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 5207
    Prev
    Next
    INDEX
    Explanations

    investment amounts and planning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /
    0.70
    activity
    0.69
    azone
    0.67
    cup
    0.64
    Constructor
    0.64
    section
    0.64
    constructor
    0.63
    action
    0.63
    animations
    0.63
     _
    0.62
    POSITIVE LOGITS
     investimento
    1.10
     plunged
    1.07
     invested
    0.98
     embarking
    0.93
     inwest
    0.92
    投資
    0.91
    Inicial
    0.89
     invests
    0.88
     دولار
    0.88
     Investment
    0.87
    Activations Density 0.010%

    No Known Activations