© 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. 31-GEMMASCOPE-2-RES-262K
    7. 21492
    Prev
    Next
    INDEX
    Explanations

    possession, others, necessities

    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_31_width_262k_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
     microtub
    0.39
     t
    0.37
     surgical
    0.36
     boron
    0.35
     led
    0.35
    ことを
    0.34
     biocompat
    0.34
     lm
    0.33
     स
    0.33
     software
    0.33
    POSITIVE LOGITS
    પો
    0.41
    。
    0.41
    си
    0.39
    acidade
    0.38
    ախ
    0.38
    仇
    0.38
    лық
    0.38
    तिथि
    0.38
    αι
    0.36
    сион
    0.36
    Activations Density 0.078%

    No Known Activations