© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8567
    Prev
    Next
    INDEX
    Explanations

    dissolving and fading

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     chill
    0.47
     flipped
    0.46
     injure
    0.44
     cured
    0.43
     togg
    0.43
     wounded
    0.42
     lô
    0.42
    뗀
    0.42
     injured
    0.41
    Chill
    0.41
    POSITIVE LOGITS
     dissolving
    1.31
     dissolves
    1.30
     dissolve
    1.30
     dissolution
    1.28
    溶解
    1.13
     dissolved
    1.13
     раство
    1.05
     disintegr
    1.04
     dissol
    1.01
     melting
    1.01
    Activations Density 0.261%

    No Known Activations