© 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. 31-GEMMASCOPE-2-RES-262K
    4. 76964
    Prev
    Next
    INDEX
    Explanations

    second address

    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
     southern
    0.40
             
    0.39
     leaves
    0.38
     South
    0.37
     rules
    0.37
     rounded
    0.37
     several
    0.37
    本
    0.37
     curators
    0.37
     seven
    0.36
    POSITIVE LOGITS
    Oréal
    0.53
    ()].
    0.51
     एपिसोड
    0.50
    (,
    0.50
    ']].
    0.49
    خد
    0.48
     affrontare
    0.47
     episódio
    0.47
    🌪
    0.47
     humanas
    0.45
    Activations Density 0.005%

    No Known Activations