© 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. 137964
    Prev
    Next
    INDEX
    Explanations

    climbing and scaling

    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
     الرحمن
    0.66
     Keating
    0.61
     yakın
    0.61
     Nasional
    0.59
    ع
    0.59
     Cashback
    0.58
    لی
    0.57
    קה
    0.57
    ﻪ
    0.57
    ั่ง
    0.56
    POSITIVE LOGITS
     ladders
    0.69
     climb
    0.64
     ladder
    0.62
     climbing
    0.59
     climbers
    0.59
     ambiguities
    0.57
     escalera
    0.57
    해야
    0.55
    爬
    0.54
     climbed
    0.52
    Activations Density 0.006%

    No Known Activations