© 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. 66080
    Prev
    Next
    INDEX
    Explanations

    on dates or specific words

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

    massive financial and cultural phenomena

    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
    ,
    0.47
     Torres
    0.47
     Yoh
    0.45
     Rocha
    0.45
     López
    0.43
     A
    0.43
     Does
    0.43
    ственная
    0.43
     Kelly
    0.42
     Stein
    0.41
    POSITIVE LOGITS
    rafpunkte
    0.59
    daten
    0.50
    dateTime
    0.48
    дати
    0.46
    amending
    0.46
    μοσ
    0.46
    🕛
    0.45
    𝓼
    0.44
    ONDON
    0.44
    𝙊
    0.43
    Activations Density 0.000%

    No Known Activations