© 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. 14269
    Prev
    Next
    INDEX
    Explanations

    except closed available

    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
     tulee
    2.77
    erjee
    2.70
    ⠛
    2.67
     dále
    2.67
     idha
    2.65
     ruộng
    2.64
    𝐝
    2.64
     phẳng
    2.62
    ر
    2.58
    م
    2.55
    POSITIVE LOGITS
    ยิน
    2.28
    ​—
    2.18
    lectic
    2.16
     departing
    2.08
     FIG
    2.06
    ▂
    2.06
    ✩
    2.05
    smart
    2.04
    ✽
    2.04
    xsl
    2.03
    Activations Density 0.000%

    No Known Activations