© 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
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 4461
    Prev
    Next
    INDEX
    Explanations

    switch between options

    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
    า
    1.25
    ي
    1.13
    ge
    1.08
    kap
    1.05
    ;
    1.03
    ة
    1.02
    지
    1.00
     a
    1.00
    z
    0.96
    ne
    0.96
    POSITIVE LOGITS
    ول
    1.27
    ’
    1.22
     switches
    1.21
     switched
    1.13
    ᱘
    1.13
    ບບ
    1.06
     with
    1.05
    ૩
    1.04
    Ꮦ
    1.03
    נ
    1.01
    Activations Density 0.036%

    No Known Activations