© 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-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 37
    Prev
    Next
    INDEX
    Explanations

    energy field, audio signal, magma behaves

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_width_16k_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
    3
    0.73
     empresas
    0.66
    2
    0.64
    9
    0.63
    1
    0.62
    0
    0.61
    8
    0.61
     contratar
    0.60
     escritorio
    0.59
    7
    0.58
    POSITIVE LOGITS
     frequency
    1.13
     durations
    1.10
     frequencies
    1.08
     sequences
    1.07
     duration
    1.07
     sequence
    1.07
    duration
    1.07
     inhibition
    1.07
     initiation
    1.07
    <unused765>
    1.04
    Activations Density 4.972%

    No Known Activations