© 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. 14158
    Prev
    Next
    INDEX
    Explanations

    sum of squares

    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
    นต์
    2.71
    defining
    2.44
     पक्ष
    2.42
    }$\\
    2.32
     fowl
    2.27
     ספר
    2.26
    dataFormat
    2.22
    輋
    2.20
    alta
    2.19
    alty
    2.18
    POSITIVE LOGITS
    cadilly
    2.63
    ٽ
    2.40
    েশন
    2.40
    セミ
    2.35
    oprec
    2.25
    helia
    2.21
    nije
    2.12
    ″
    2.11
    ynitrite
    2.09
    gave
    2.08
    Activations Density 0.003%

    No Known Activations