© 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. 1596
    Prev
    Next
    INDEX
    Explanations

    past tense or temporal references

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

    identifying potential evolution

    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
     tonight
    0.22
     this
    0.21
     हैं
    0.21
     এবারের
    0.20
     tomorrow
    0.19
     আপাতত
    0.19
    今回の
    0.19
     ♡
    0.19
     awaits
    0.19
     이번
    0.19
    POSITIVE LOGITS
     damals
    0.30
     buvo
    0.28
     erano
    0.27
     aveva
    0.26
     avevano
    0.26
    當時
    0.25
     vardı
    0.25
     avait
    0.25
     hadde
    0.25
     είχε
    0.25
    Activations Density 0.000%

    No Known Activations