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-3-1B
    3. 13-GEMMASCOPE-2-RES-16K
    4. 3995
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    k
    1.46
    in
    1.40
    h
    1.28
    es
    1.28
    ast
    1.27
    akan
    1.26
    idan
    1.26
    akah
    1.25
    inan
    1.24
    als
    1.23
    POSITIVE LOGITS
    లంగాణ
    2.09
    𒋢
    2.03
    Presets
    2.01
     इम्मे
    2.00
    𒊏
    2.00
    Aslamualaikum
    2.00
     mighty
    1.98
    𒁾
    1.97
    𐰣
    1.97
     ましょう
    1.96
    Activations Density 1.608%

    No Known Activations