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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2382
    Prev
    Next
    INDEX
    Explanations

    crisis hotlines

    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_22_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
     tenté
    0.76
    ᵚ
    0.76
     drier
    0.75
    ႆ
    0.73
     destinado
    0.73
    더라도
    0.72
    ‖</
    0.72
    管理的
    0.71
     mög
    0.71
     હોય
    0.70
    POSITIVE LOGITS
    éc
    0.68
    color
    0.68
     whales
    0.68
    ettes
    0.66
    COLOR
    0.64
    al
    0.63
     পেট
    0.61
    alista
    0.60
    I
    0.60
    galactos
    0.60
    Activations Density 0.105%

    No Known Activations