© 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. 34-GEMMASCOPE-RES-131K
    7. 54177
    Prev
    Next
    INDEX
    Explanations

    need to register, enable, sign, install, login

    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
     intentar
    -1.16
     Attempt
    -1.08
    Attempt
    -1.07
     attempting
    -1.05
     trying
    -1.03
     Trying
    -1.02
    aliere
    -1.00
     not
    -0.99
    attempt
    -0.98
     any
    -0.96
    POSITIVE LOGITS
     know
    1.59
     yourself
    1.28
     remember
    1.23
    either
    1.22
    remember
    1.22
     хорошего
    1.13
    懂
    1.13
     either
    1.13
     understand
    1.08
     wait
    1.06
    Activations Density 0.064%

    No Known Activations