© 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. 18978
    Prev
    Next
    INDEX
    Explanations

    concepts like praise, himself, mystery, stuff, hope

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

    past time loss

    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
    CollectedField
    0.43
     desk
    0.42
    PanelVisual
    0.41
    紺
    0.40
    ﺀ
    0.40
    iac
    0.40
    などが
    0.40
     ユ
    0.40
    pronged
    0.40
     strikingly
    0.39
    POSITIVE LOGITS
     atividade
    0.50
     dns
    0.45
     distância
    0.44
    قتها
    0.43
    是要
    0.43
     adata
    0.43
     Downloads
    0.43
    aktionen
    0.43
    بعد
    0.42
    чных
    0.42
    Activations Density 0.000%

    No Known Activations