© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 40667
    Prev
    Next
    INDEX
    Explanations

    mother's day contexts and actions

    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_16_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
    وڈ
    1.20
    are
    1.13
    و
    1.12
    os
    1.11
    ak
    1.05
     impuesto
    1.05
    emen
    1.03
    다
    1.02
    ین
    1.00
    து
    1.00
    POSITIVE LOGITS
     mother
    1.38
     of
    1.30
    h
    1.24
     Mother
    1.16
    3
    1.12
     Mutter
    1.09
     with
    1.08
     moeder
    1.07
     that
    1.06
    Y
    1.03
    Activations Density 0.014%

    No Known Activations