© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48984
    Prev
    Next
    INDEX
    Explanations

    able to

    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_34/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
     عدة
    -1.35
     Trotzdem
    -1.23
     Deshalb
    -1.16
     чтоб
    -1.16
     schmerz
    -1.14
     např
    -1.13
     др
    -1.12
     trotz
    -1.11
    只需
    -1.09
     thru
    -1.05
    POSITIVE LOGITS
    能够
    1.29
    Plenty
    1.21
     coloro
    1.21
     solamente
    1.18
    }
    1.18
     içerisinde
    1.15
    但却
    1.13
    的时候
    1.13
     insofar
    1.13
    しっかりと
    1.12
    Activations Density 0.215%

    No Known Activations