© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 14033
    Prev
    Next
    INDEX
    Explanations

    recognizing or acknowledging something

    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
    Er
    2.40
     Er
    2.33
    痫
    2.13
    INGTON
    2.09
    ed
    2.09
    undance
    2.07
    raum
    2.05
     lintas
    2.02
     đạp
    2.02
    strom
    2.01
    POSITIVE LOGITS
    atat
    3.12
    𝘨
    3.08
    riever
    2.99
     വേ
    2.92
     goble
    2.90
    𝗘
    2.80
    䡏
    2.79
    緎
    2.78
    ataya
    2.78
     ongles
    2.75
    Activations Density 0.031%

    No Known Activations