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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 111723
    Prev
    Next
    INDEX
    Explanations

    this trend

    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_40_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
     sombras
    0.44
     revisit
    0.43
     INTERVAL
    0.43
     pourcentage
    0.41
     Германии
    0.41
    볐
    0.40
    निर्भर
    0.40
     monatomic
    0.40
     flops
    0.39
    势
    0.39
    POSITIVE LOGITS
    ppe
    0.42
    Hil
    0.40
    base
    0.39
    wad
    0.38
    vasion
    0.37
    aad
    0.36
    盜
    0.36
    essed
    0.35
    nta
    0.35
     Benn
    0.35
    Activations Density 0.000%

    No Known Activations