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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 2382
    Prev
    Next
    INDEX
    Explanations

    longterm or permanent qualities

    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_17_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
    Errorf
    0.68
     চৈতন্য
    0.66
     whitespace
    0.63
     whis
    0.62
    ভাগে
    0.62
    ienze
    0.61
    慌
    0.61
    ショ
    0.60
     underweight
    0.60
    飛び
    0.59
    POSITIVE LOGITS
     permanent
    2.32
     lasting
    2.25
     longterm
    2.11
    permanent
    2.08
     Permanent
    2.02
     enduring
    2.01
    Permanent
    2.00
     permanente
    1.99
     permanence
    1.96
     everlasting
    1.95
    Activations Density 1.328%

    No Known Activations