© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8934
    Prev
    Next
    INDEX
    Explanations

    which is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h5>
    1.09
    』
    1.02
    </sup>
    1.01
    orh
    0.99
    】
    0.98
    }\
    0.96
    </h1>
    0.94
    }-\
    0.94
     тоже
    0.93
     usw
    0.93
    POSITIVE LOGITS
     foundational
    1.40
     굉장히
    1.40
     terlebih
    1.35
     extrêmement
    1.32
     baseline
    1.27
     spanning
    1.26
     impactful
    1.25
     extremamente
    1.24
     erstmal
    1.23
     situational
    1.22
    Activations Density 0.253%

    No Known Activations