© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-4B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 4426
    Prev
    Next
    INDEX
    Explanations

    different archetypes, roles, or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_17_width_16k_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
     Highlights
    0.94
     angegeben
    0.92
    大量
    0.91
    Miscellaneous
    0.91
    概述
    0.90
     discussão
    0.89
     👍
    0.88
     Discussions
    0.88
    唓
    0.87
    Options
    0.87
    POSITIVE LOGITS
     archetype
    1.16
     heroes
    1.16
     metaphorical
    1.11
     warrior
    1.08
     aristocratic
    1.07
     villains
    1.06
     hero
    1.05
     warriors
    1.05
     aristocracy
    1.04
    heroes
    1.03
    Activations Density 0.129%

    No Known Activations