© 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-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 88862
    Prev
    Next
    INDEX
    Explanations

    writing articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     previs
    0.45
    0.43
     Trung
    0.43
    Trung
    0.42
     trung
    0.42
    əri
    0.42
     ESR
    0.41
     celebs
    0.41
    媺
    0.41
     disposiciones
    0.41
    POSITIVE LOGITS
     装
    0.48
    ],
    0.47
    ه
    0.47
    শো
    0.47
     politique
    0.46
    seqNum
    0.46
    챱
    0.46
    taining
    0.45
     संदेह
    0.45
    UpdateChoice
    0.45
    Activations Density 0.000%

    No Known Activations