© 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. 229052
    Prev
    Next
    INDEX
    Explanations

    currency and time references

    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
     on
    0.53
    5
    0.52
    in
    0.47
     duplicated
    0.45
    btn
    0.45
     in
    0.44
     Bello
    0.44
     said
    0.43
     put
    0.42
     mend
    0.42
    POSITIVE LOGITS
    䢀
    0.56
    𝘐
    0.53
    沨
    0.52
    Вели
    0.49
    㧋
    0.49
    犾
    0.49
    Athena
    0.47
     મહ
    0.47
    انہوں
    0.47
    𝓾
    0.47
    Activations Density 0.002%

    No Known Activations