© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 4714
    Prev
    Next
    INDEX
    Explanations

    compound interest formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    lyan
    0.45
    ~)
    0.44
    InitFlag
    0.44
    thisobject
    0.41
    ColorLegend
    0.41
     quei
    0.41
    thom
    0.41
     Pto
    0.40
    稃
    0.39
    \%)
    0.39
    POSITIVE LOGITS
     grows
    0.43
     gains
    0.43
     gagner
    0.42
     gain
    0.42
     increment
    0.42
     growth
    0.41
     groovy
    0.41
     conservatory
    0.40
    增
    0.40
     barista
    0.40
    Activations Density 0.001%

    No Known Activations