© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 200877
    Prev
    Next
    INDEX
    Explanations

    pointing to other items

    np_acts-logits-general · gemini-2.5-flash-lite

    other references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mourn
    0.55
     サイド
    0.49
     enig
    0.48
    ዮ
    0.48
     sporadically
    0.48
     التمرين
    0.46
     秦
    0.46
     سن
    0.46
     რამდენ
    0.46
     سره
    0.45
    POSITIVE LOGITS
    ittää
    0.43
    いただいた
    0.42
    गी
    0.41
    शी
    0.38
    蚬
    0.38
    빠
    0.37
    閫
    0.37
    ittee
    0.36
    ัว
    0.36
     Offering
    0.36
    Activations Density 0.000%

    No Known Activations