© 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. 3468
    Prev
    Next
    INDEX
    Explanations

    measurement and distance

    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
     ancient
    1.23
     **
    1.17
     subtle
    1.16
     complex
    1.16
     [
    1.15
     specific
    1.10
     something
    1.10
     nuanced
    1.10
     sentiment
    1.09
     existential
    1.09
    POSITIVE LOGITS
    In
    1.84
    An
    1.80
    Res
    1.71
    End
    1.68
    Re
    1.67
    Ad
    1.66
    Car
    1.65
    St
    1.64
    Generate
    1.63
    T
    1.61
    Activations Density 0.331%

    No Known Activations