© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 35075
    Prev
    Next
    INDEX
    Explanations

    friends, followers, following

    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_22/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
     our
    -1.15
     design
    -1.09
    KeyId
    -1.08
     бренда
    -1.06
     depan
    -1.01
     continua
    -1.00
    牲
    -0.99
    styrelsen
    -0.98
     lar
    -0.98
    ċ
    -0.98
    POSITIVE LOGITS
     whom
    1.24
     friends
    1.16
    一愣
    1.10
     persönliche
    1.09
    pantalon
    1.08
    お世話
    1.07
     who
    1.06
     mutual
    1.05
     établi
    1.05
    pantal
    1.04
    Activations Density 0.009%

    No Known Activations