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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5822
    Prev
    Next
    INDEX
    Explanations

    explanation or how to explain

    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_31_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
     metastases
    0.42
    ेलो
    0.41
     Complexes
    0.40
     interesses
    0.39
     néhány
    0.39
    ❷
    0.39
     complexes
    0.39
     hadrons
    0.39
     aneu
    0.38
    ⸨
    0.38
    POSITIVE LOGITS
    ana
    0.46
    ta
    0.41
    ida
    0.41
    ata
    0.40
    or
    0.40
     explanation
    0.40
    explain
    0.39
    ng
    0.39
    ly
    0.39
    explanation
    0.39
    Activations Density 0.269%

    No Known Activations