© 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-65K
    7. 62075
    Prev
    Next
    INDEX
    Explanations

    roughly 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_65k_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
     Displaystyle
    0.52
    ^+$
    0.45
     andRow
    0.45
     Gas
    0.44
     Omega
    0.43
     Theorie
    0.43
     Om
    0.43
     Formal
    0.43
     }}(
    0.42
     produk
    0.42
    POSITIVE LOGITS
    どうか
    0.44
    calend
    0.44
     звер
    0.43
    ਦੀ
    0.42
    خذ
    0.41
     téléphonique
    0.40
    進行
    0.40
    相談
    0.40
     لار
    0.40
    ልቅ
    0.40
    Activations Density 0.010%

    No Known Activations