© 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. 101583
    Prev
    Next
    INDEX
    Explanations

    selfishness, funding, dreams

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

    bad endings

    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
     ብዙውን
    0.49
    ⤠
    0.46
    笕
    0.44
     பெரும்பாலான
    0.44
    嘻
    0.44
    Jdk
    0.44
     வழ
    0.44
    Skippable
    0.44
    Сред
    0.44
    禄
    0.44
    POSITIVE LOGITS
     selfishness
    0.54
     selfish
    0.48
     metastasis
    0.46
     controversy
    0.46
     pob
    0.45
     reborn
    0.45
     amni
    0.45
     metastases
    0.44
     anchorage
    0.44
     sorti
    0.44
    Activations Density 0.008%

    No Known Activations