© 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. 7-GEMMASCOPE-2-RES-16K
    7. 152
    Prev
    Next
    INDEX
    Explanations

    listening without judgment

    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_7_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
     u
    1.52
     ho
    1.50
     weep
    1.33
     getters
    1.23
     difficult
    1.22
     tract
    1.22
     rude
    1.22
     uj
    1.21
     Χ
    1.19
     iv
    1.19
    POSITIVE LOGITS
    सेशन
    1.91
    étera
    1.89
    ፈጥ
    1.85
    údo
    1.83
     biologique
    1.81
    ア
    1.81
    ช่วง
    1.77
     velocidade
    1.77
     reveló
    1.76
    Aless
    1.76
    Activations Density 0.129%

    No Known Activations