© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57539
    Prev
    Next
    INDEX
    Explanations

    freeze, frozen, freezing

    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
     siguiente
    -0.97
    珩
    -0.86
     erased
    -0.81
     Herausgeber
    -0.81
    支払い
    -0.81
     podem
    -0.81
     nuestros
    -0.80
     Fabrication
    -0.80
    崛起
    -0.79
     understand
    -0.79
    POSITIVE LOGITS
     freeze
    2.59
    freeze
    2.53
    Freeze
    2.41
     Freeze
    2.41
     freezes
    2.19
    冻
    2.19
    frozen
    2.17
     freezing
    2.14
     froze
    2.13
     frozen
    2.09
    Activations Density 0.012%

    No Known Activations