© 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. 31-GEMMASCOPE-2-RES-262K
    7. 111711
    Prev
    Next
    INDEX
    Explanations

    cannot display image here

    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_31_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
     confidentiality
    0.49
     privacy
    0.44
     (
    0.41
     gossip
    0.40
     confidential
    0.38
     zdrow
    0.38
     confidence
    0.38
     when
    0.37
     what
    0.37
     leave
    0.37
    POSITIVE LOGITS
    但是在
    0.50
    但我
    0.47
    但是我
    0.46
     โจทย์
    0.45
    ᅴ
    0.44
    ActionBar
    0.43
     fistule
    0.42
    きた
    0.42
     بالټ
    0.41
     Elektrokh
    0.40
    Activations Density 0.017%

    No Known Activations