© 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. 48764
    Prev
    Next
    INDEX
    Explanations

    thus far or so far

    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
     superare
    -1.21
     rimanere
    -0.99
     rispondere
    -0.91
     partecipare
    -0.91
     lasciare
    -0.90
     offrire
    -0.89
     diventare
    -0.87
     lavorare
    -0.87
     imparare
    -0.85
    کند
    -0.82
    POSITIVE LOGITS
     far
    3.39
    far
    2.14
     далеко
    1.74
    Far
    1.57
     Far
    1.53
    FAR
    1.36
    ofar
    1.35
    远
    1.32
     daleko
    1.30
     FAR
    1.20
    Activations Density 0.025%

    No Known Activations