Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 2658
    Prev
    Next
    INDEX
    Explanations

    but then it grew on me

    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
    Obj
    0.33
    ®
    0.33
    劑
    0.33
     flammable
    0.32
    剤
    0.32
    Ⓡ
    0.32
    ®,
    0.31
     hydrodynamic
    0.31
     acceler
    0.31
     tapes
    0.31
    POSITIVE LOGITS
     Blog
    0.38
     blog
    0.36
    Ⲕ
    0.36
    네요
    0.36
    Ⲣ
    0.35
     newbie
    0.35
     bloggers
    0.35
    敺
    0.34
     Politiker
    0.34
    Ⲥ
    0.34
    Activations Density 0.001%

    No Known Activations