© 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. 22-GEMMASCOPE-2-RES-16K
    7. 594
    Prev
    Next
    INDEX
    Explanations

    надежно подключен / безнадежность / надежда

    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_22_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
     ur
    0.76
     X
    0.76
     –
    0.75
     ill
    0.75
    0.71
     into
    0.69
     T
    0.68
    –
    0.68
     real
    0.67
     PM
    0.66
    POSITIVE LOGITS
    <unused799>
    1.44
    ൮
    1.36
    <unused810>
    1.36
    ࢯ
    1.35
    SRPCS
    1.35
    mataspid
    1.35
    <unused819>
    1.34
    <unused117>
    1.33
    <unused813>
    1.33
    ꗤ
    1.33
    Activations Density 0.062%

    No Known Activations