© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 16607
    Prev
    Next
    INDEX
    Explanations

    ever + past tense verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     neuer
    0.92
     newfound
    0.85
     doo
    0.85
     दौरान
    0.82
    它
    0.82
     podczas
    0.80
    ्मी
    0.80
    ITION
    0.79
     helm
    0.78
     medis
    0.78
    POSITIVE LOGITS
    an
    0.96
    es
    0.80
    um
    0.79
    ब
    0.76
    ان
    0.75
    ὠ
    0.75
    モン
    0.73
    ʖ
    0.71
    nt
    0.71
    اد
    0.71
    Activations Density 0.001%

    No Known Activations