© 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. 128045
    Prev
    Next
    INDEX
    Explanations

    phrases following certain words

    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
    ຸນ
    0.44
     następnie
    0.43
     također
    0.43
     করিয়াছেন
    0.41
     қол
    0.41
     করিয়াছিলেন
    0.40
    <0xAC>
    0.40
    保证
    0.40
    வைப்
    0.40
     siècles
    0.40
    POSITIVE LOGITS
     PTSD
    0.42
     psychiatrist
    0.42
     kicks
    0.41
     leaks
    0.41
     neurom
    0.41
     indoct
    0.41
     indoctr
    0.41
     IBS
    0.40
     pumps
    0.40
     Gaines
    0.40
    Activations Density 0.011%

    No Known Activations