© 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. 193
    Prev
    Next
    INDEX
    Explanations

    predictability of timing

    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
    >→</
    1.70
    ASF
    1.51
    
    1.49
    ோருக்கு
    1.48
    esin
    1.45
    딩
    1.45
    ENIX
    1.44
     BEA
    1.43
    دين
    1.41
    pictureBox
    1.41
    POSITIVE LOGITS
     harmonic
    1.90
    稠
    1.72
    urnal
    1.63
    conder
    1.59
    imal
    1.59
    ريب
    1.58
    quisa
    1.58
    idal
    1.55
     logarithm
    1.55
    లా
    1.55
    Activations Density 0.000%

    No Known Activations