© 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. 66603
    Prev
    Next
    INDEX
    Explanations

    continuing story or staff find

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

    explaining 1+1=3

    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
    ᆻ
    0.58
    蟻
    0.52
     стаў
    0.49
    いました
    0.48
     کی۔
    0.48
    刽
    0.47
     نہیں۔
    0.47
     ().
    0.47
     সব্ব
    0.47
    JC
    0.46
    POSITIVE LOGITS
     NPS
    0.45
     müs
    0.45
     témoign
    0.40
    iton
    0.40
    azepam
    0.40
    urende
    0.39
     complained
    0.39
    經常
    0.39
     Nim
    0.39
     grouse
    0.39
    Activations Density 0.001%

    No Known Activations