© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 5179
    Prev
    Next
    INDEX
    Explanations

    reporting or attributing statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_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
    ơm
    0.70
     expressed
    0.70
     સત
    0.65
     saying
    0.65
    صی
    0.65
    expressed
    0.64
     bä
    0.64
    ฝ
    0.63
    uma
    0.63
    ena
    0.62
    POSITIVE LOGITS
     officials
    1.12
     researchers
    1.11
     reviewers
    0.94
     according
    0.93
     investigators
    0.93
     investigadores
    0.92
     critics
    0.91
     उन्होंने
    0.91
     they
    0.89
    によっては
    0.88
    Activations Density 0.009%

    No Known Activations