© 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. 57843
    Prev
    Next
    INDEX
    Explanations

    if needed or necessary

    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
    Dichloroprop
    -1.08
     visuel
    -1.06
     meub
    -1.06
    aaaaaaaa
    -1.03
     loob
    -1.02
     求
    -1.01
    ſts
    -1.00
     teknis
    -1.00
     solide
    -0.99
    GetType
    -0.98
    POSITIVE LOGITS
     needed
    7.22
     necessary
    6.06
    needed
    4.81
     required
    4.75
     Needed
    4.34
     need
    4.09
    Needed
    4.00
    necessary
    3.84
     necesario
    3.80
     nodig
    3.70
    Activations Density 0.041%

    No Known Activations