© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 131066
    Prev
    Next
    INDEX
    Explanations

    release from obligations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    仕上がり
    -1.00
    ̣t
    -0.96
    いかに
    -0.94
    知り
    -0.92
     Such
    -0.92
    typeof
    -0.90
     Orgel
    -0.90
     enfermera
    -0.90
    夀
    -0.88
    过去了
    -0.88
    POSITIVE LOGITS
     from
    1.33
    所有
    1.13
     responsibility
    1.05
    ４
    1.05
    responsibility
    1.02
     coreano
    1.02
     Nedir
    1.02
    jednoc
    1.02
    甚至
    1.02
     freeing
    1.02
    Activations Density 0.045%

    No Known Activations