© 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. 48733
    Prev
    Next
    INDEX
    Explanations

    something prior

    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
    今は
    -0.92
     Later
    -0.87
    现在的
    -0.85
    }=\
    -0.84
    Later
    -0.82
    第
    -0.82
    桃
    -0.81
    wüns
    -0.81
     позже
    -0.81
    Dopo
    -0.81
    POSITIVE LOGITS
     prior
    7.28
    prior
    5.59
    Prior
    5.41
     Prior
    5.22
     PRIOR
    4.53
     previous
    4.25
    PRIOR
    4.09
     preceding
    3.64
     предыду
    3.13
     priors
    3.03
    Activations Density 0.247%

    No Known Activations