© 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
    2. Gemma-3-12B
    3. 41-GEMMASCOPE-2-RES-262K
    4. 241494
    Prev
    Next
    INDEX
    Explanations

    stable unchanging

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_262k_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
    flora
    0.58
    JUN
    0.54
    Flora
    0.54
    MIX
    0.53
     puedas
    0.52
    infiltration
    0.51
     इसे
    0.51
    >()
    0.51
    Bella
    0.51
    anesu
    0.50
    POSITIVE LOGITS
     stable
    0.74
     fixed
    0.67
     stationary
    0.63
     mindful
    0.62
     stably
    0.61
     respectful
    0.61
    ewhere
    0.59
     фикси
    0.59
     Stable
    0.59
     固定
    0.58
    Activations Density 0.000%

    No Known Activations