© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105876
    Prev
    Next
    INDEX
    Explanations

    specific entities and categories

    np_acts-logits-general · gemini-2.5-flash-lite

    emotional states and vulnerability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    മാർ
    0.48
    മാര്‍
    0.48
     chargers
    0.45
    сторон
    0.44
    మార్
    0.44
     briefings
    0.44
    証
    0.43
     Schnell
    0.42
     recherches
    0.42
    ન
    0.41
    POSITIVE LOGITS
    traj
    0.54
    estomac
    0.53
    latency
    0.52
    াবে
    0.48
    aculate
    0.48
     τραγ
    0.48
    >[]
    0.47
     flowed
    0.47
    msub
    0.47
    tp
    0.46
    Activations Density 0.001%

    No Known Activations